rm old configs

chat_template.jinja

@@ -1,331 +0,0 @@
-{#-
-  In addition to the normal inputs of `messages` and `tools`, this template also accepts the
-  following kwargs:
-  - "builtin_tools": A list, can contain "browser" and/or "python".
-  - "model_identity": A string that optionally describes the model identity.
-  - "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
- #}
-
-{#- Tool Definition Rendering ============================================== #}
-{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
-    {%- if param_spec.type == "array" -%}
-        {%- if param_spec['items'] -%}
-            {%- if param_spec['items']['type'] == "string" -%}
-                {{- "string[]" }}
-            {%- elif param_spec['items']['type'] == "number" -%}
-                {{- "number[]" }}
-            {%- elif param_spec['items']['type'] == "integer" -%}
-                {{- "number[]" }}
-            {%- elif param_spec['items']['type'] == "boolean" -%}
-                {{- "boolean[]" }}
-            {%- else -%}
-                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
-                {%- if inner_type == "object | object" or inner_type|length > 50 -%}
-                    {{- "any[]" }}
-                {%- else -%}
-                    {{- inner_type + "[]" }}
-                {%- endif -%}
-            {%- endif -%}
-            {%- if param_spec.nullable -%}
-                {{- " | null" }}
-            {%- endif -%}
-        {%- else -%}
-            {{- "any[]" }}
-            {%- if param_spec.nullable -%}
-                {{- " | null" }}
-            {%- endif -%}
-        {%- endif -%}
-    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
-        {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
-        {%- if param_spec.type | length > 1 -%}
-            {{- param_spec.type | join(" | ") }}
-        {%- else -%}
-            {{- param_spec.type[0] }}
-        {%- endif -%}
-    {%- elif param_spec.oneOf -%}
-        {#- Handle oneOf schemas - check for complex unions and fallback to any #}
-        {%- set has_object_variants = false -%}
-        {%- for variant in param_spec.oneOf -%}
-            {%- if variant.type == "object" -%}
-                {%- set has_object_variants = true -%}
-            {%- endif -%}
-        {%- endfor -%}
-        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
-            {{- "any" }}
-        {%- else -%}
-            {%- for variant in param_spec.oneOf -%}
-                {{- render_typescript_type(variant, required_params) -}}
-                {%- if variant.description %}
-                    {{- "// " + variant.description }}
-                {%- endif -%}
-                {%- if variant.default is defined %}
-                    {{ "// default: " + variant.default|tojson }}
-                {%- endif -%}
-                {%- if not loop.last %}
-                    {{- " | " }}
-                {% endif -%}
-            {%- endfor -%}
-        {%- endif -%}
-    {%- elif param_spec.type == "string" -%}
-        {%- if param_spec.enum -%}
-            {{- '"' + param_spec.enum|join('" | "') + '"' -}}
-        {%- else -%}
-            {{- "string" }}
-            {%- if param_spec.nullable %}
-                {{- " | null" }}
-            {%- endif -%}
-        {%- endif -%}
-    {%- elif param_spec.type == "number" -%}
-        {{- "number" }}
-    {%- elif param_spec.type == "integer" -%}
-        {{- "number" }}
-    {%- elif param_spec.type == "boolean" -%}
-        {{- "boolean" }}
-
-    {%- elif param_spec.type == "object" -%}
-        {%- if param_spec.properties -%}
-            {{- "{\n" }}
-            {%- for prop_name, prop_spec in param_spec.properties.items() -%}
-                {{- prop_name -}}
-                {%- if prop_name not in (param_spec.required or []) -%}
-                    {{- "?" }}
-                {%- endif -%}
-                {{- ": " }}
-                {{ render_typescript_type(prop_spec, param_spec.required or []) }}
-                {%- if not loop.last -%}
-                    {{-", " }}
-                {%- endif -%}
-            {%- endfor -%}
-            {{- "}" }}
-        {%- else -%}
-            {{- "object" }}
-        {%- endif -%}
-    {%- else -%}
-        {{- "any" }}
-    {%- endif -%}
-{%- endmacro -%}
-
-{%- macro render_tool_namespace(namespace_name, tools) -%}
-    {{- "## " + namespace_name + "\n\n" }}
-    {{- "namespace " + namespace_name + " {\n\n" }}
-    {%- for tool in tools %}
-        {%- set tool = tool.function %}
-        {{- "// " + tool.description + "\n" }}
-        {{- "type "+ tool.name + " = " }}
-        {%- if tool.parameters and tool.parameters.properties %}
-            {{- "(_: {\n" }}
-            {%- for param_name, param_spec in tool.parameters.properties.items() %}
-                {%- if param_spec.description %}
-                    {{- "// " + param_spec.description + "\n" }}
-                {%- endif %}
-                {{- param_name }}
-                {%- if param_name not in (tool.parameters.required or []) -%}
-                    {{- "?" }}
-                {%- endif -%}
-                {{- ": " }}
-                {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
-                {%- if param_spec.default is defined -%}
-                    {%- if param_spec.enum %}
-                        {{- ", // default: " + param_spec.default }}
-                    {%- elif param_spec.oneOf %}
-                        {{- "// default: " + param_spec.default }}
-                    {%- else %}
-                        {{- ", // default: " + param_spec.default|tojson }}
-                    {%- endif -%}
-                {%- endif -%}
-                {%- if not loop.last %}
-                    {{- ",\n" }}
-                {%- else %}
-                    {{- ",\n" }}
-                {%- endif -%}
-            {%- endfor %}
-            {{- "}) => any;\n\n" }}
-        {%- else -%}
-            {{- "() => any;\n\n" }}
-        {%- endif -%}
-    {%- endfor %}
-    {{- "} // namespace " + namespace_name }}
-{%- endmacro -%}
-
-{%- macro render_builtin_tools(browser_tool, python_tool) -%}
-    {%- if browser_tool %}
-        {{- "## browser\n\n" }}
-        {{- "// Tool for browsing.\n" }}
-        {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
-        {{- "// Cite information from the tool using the following format:\n" }}
-        {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
-        {{- "// Do not quote more than 10 words directly from the tool output.\n" }}
-        {{- "// sources=web (default: web)\n" }}
-        {{- "namespace browser {\n\n" }}
-        {{- "// Searches for information related to `query` and displays `topn` results.\n" }}
-        {{- "type search = (_: {\n" }}
-        {{- "query: string,\n" }}
-        {{- "topn?: number, // default: 10\n" }}
-        {{- "source?: string,\n" }}
-        {{- "}) => any;\n\n" }}
-        {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
-        {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
-        {{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
-        {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
-        {{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
-        {{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
-        {{- "type open = (_: {\n" }}
-        {{- "id?: number | string, // default: -1\n" }}
-        {{- "cursor?: number, // default: -1\n" }}
-        {{- "loc?: number, // default: -1\n" }}
-        {{- "num_lines?: number, // default: -1\n" }}
-        {{- "view_source?: boolean, // default: false\n" }}
-        {{- "source?: string,\n" }}
-        {{- "}) => any;\n\n" }}
-        {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
-        {{- "type find = (_: {\n" }}
-        {{- "pattern: string,\n" }}
-        {{- "cursor?: number, // default: -1\n" }}
-        {{- "}) => any;\n\n" }}
-        {{- "} // namespace browser\n\n" }}
-    {%- endif -%}
-
-    {%- if python_tool %}
-        {{- "## python\n\n" }}
-        {{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
-        {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
-    {%- endif -%}
-{%- endmacro -%}
-
-{#- System Message Construction ============================================ #}
-{%- macro build_system_message() -%}
-    {%- if model_identity is not defined %}
-        {%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
-    {%- endif %}
-    {{- model_identity + "\n" }}
-    {{- "Knowledge cutoff: 2024-06\n" }}
-    {{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
-    {%- if reasoning_effort is not defined %}
-        {%- set reasoning_effort = "medium" %}
-    {%- endif %}
-    {{- "Reasoning: " + reasoning_effort + "\n\n" }}
-    {%- if builtin_tools %}
-        {{- "# Tools\n\n" }}
-        {%- set available_builtin_tools = namespace(browser=false, python=false) %}
-        {%- for tool in builtin_tools %}
-            {%- if tool == "browser" %}
-                {%- set available_builtin_tools.browser = true %}
-            {%- elif tool == "python" %}
-                {%- set available_builtin_tools.python = true %}
-            {%- endif %}
-        {%- endfor %}
-        {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
-    {%- endif -%}
-    {{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
-    {%- if tools -%}
-        {{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
-    {%- endif -%}
-{%- endmacro -%}
-
-{#- Main Template Logic ================================================= #}
-{#- Set defaults #}
-
-{#- Render system message #}
-{{- "<|start|>system<|message|>" }}
-{{- build_system_message() }}
-{{- "<|end|>" }}
-
-{#- Extract developer message #}
-{%- if messages[0].role == "developer" or messages[0].role == "system" %}
-    {%- set developer_message = messages[0].content %}
-    {%- set loop_messages = messages[1:] %}
-{%- else %}
-    {%- set developer_message = "" %}
-    {%- set loop_messages = messages %}
-{%- endif %}
-
-{#- Render developer message #}
-{%- if developer_message or tools %}
-    {{- "<|start|>developer<|message|>" }}
-    {%- if developer_message %}
-        {{- "# Instructions\n\n" }}
-        {{- developer_message }}
-        {{- "\n\n" }}
-    {%- endif %}
-    {%- if tools -%}
-        {{- "# Tools\n\n" }}
-        {{- render_tool_namespace("functions", tools) }}
-    {%- endif -%}
-    {{- "<|end|>" }}
-{%- endif %}
-
-{#- Render messages #}
-{%- set last_tool_call = namespace(name=none) %}
-{%- for message in loop_messages -%}
-    {#- At this point only assistant/user/tool messages should remain #}
-    {%- if message.role == 'assistant' -%}
-        {#- Checks to ensure the messages are being passed in the format we expect #}
-        {%- if "content" in message %}
-            {%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
-                {{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
-            {%- endif %}
-        {%- endif %}
-        {%- if "thinking" in message %}
-            {%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
-                {{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
-            {%- endif %}
-        {%- endif %}
-        {%- if "tool_calls" in message %}
-            {#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
-            {#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
-            {#- when we render CoT/analysis messages in inference. #}
-            {%- set future_final_message = namespace(found=false) %}
-            {%- for future_message in loop_messages[loop.index:] %}
-                {%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
-                    {%- set future_final_message.found = true %}
-                {%- endif %}
-            {%- endfor %}
-            {#- We assume max 1 tool call per message, and so we infer the tool call name #}
-            {#- in "tool" messages from the most recent assistant tool call name #}
-            {%- set tool_call = message.tool_calls[0] %}
-            {%- if tool_call.function %}
-                {%- set tool_call = tool_call.function %}
-            {%- endif %}
-            {%- if message.content and message.thinking %}
-                {{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
-            {%- elif message.content and not future_final_message.found %}
-                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
-            {%- elif message.thinking and not future_final_message.found %}
-                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
-            {%- endif %}
-            {{- "<|start|>assistant to=" }}
-            {{- "functions." + tool_call.name + "<|channel|>commentary " }}
-            {{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
-            {{- tool_call.arguments|tojson }}
-            {{- "<|call|>" }}
-            {%- set last_tool_call.name = tool_call.name %}
-        {%- elif loop.last and not add_generation_prompt %}
-            {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
-            {#- This is a situation that should only occur in training, never in inference. #}
-            {%- if "thinking" in message %}
-                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
-            {%- endif %}
-            {#- <|return|> indicates the end of generation, but <|end|> does not #}
-            {#- <|return|> should never be an input to the model, but we include it as the final token #}
-            {#- when training, so the model learns to emit it. #}
-            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
-        {%- else %}
-            {#- CoT is dropped during all previous turns, so we never render it for inference #}
-            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
-            {%- set last_tool_call.name = none %}
-        {%- endif %}
-    {%- elif message.role == 'tool' -%}
-        {%- if last_tool_call.name is none %}
-            {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
-        {%- endif %}
-        {{- "<|start|>functions." + last_tool_call.name }}
-        {{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
-    {%- elif message.role == 'user' -%}
-        {{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
-    {%- endif -%}
-{%- endfor -%}
-
-{#- Generation prompt #}
-{%- if add_generation_prompt -%}
-<|start|>assistant
-{%- endif -%}

config.json

@@ -1 +0,0 @@
-{"num_hidden_layers": 36, "num_experts": 128, "experts_per_token": 4, "vocab_size": 201088, "hidden_size": 2880, "intermediate_size": 2880, "swiglu_limit": 7.0, "head_dim": 64, "num_attention_heads": 64, "num_key_value_heads": 8, "sliding_window": 128, "initial_context_length": 4096, "rope_theta": 150000, "rope_scaling_factor": 32.0, "rope_ntk_alpha": 1, "rope_ntk_beta": 32}

dtypes.json

@@ -1 +0,0 @@
-{"embedding.weight": "BF16", "block.0.attn.norm.scale": "BF16", "block.0.attn.qkv.weight": "BF16", "block.0.attn.qkv.bias": "BF16", "block.0.attn.sinks": "BF16", "block.0.attn.out.weight": "BF16", "block.0.attn.out.bias": "BF16", "block.0.mlp.norm.scale": "BF16", "block.0.mlp.gate.weight": "BF16", "block.0.mlp.gate.bias": "BF16", "block.0.mlp.mlp1_weight.blocks": "FP4", "block.0.mlp.mlp1_weight.scales": "UE8", "block.0.mlp.mlp1_bias": "BF16", "block.0.mlp.mlp2_weight.blocks": "FP4", "block.0.mlp.mlp2_weight.scales": "UE8", "block.0.mlp.mlp2_bias": "BF16", "block.1.attn.norm.scale": "BF16", "block.1.attn.qkv.weight": "BF16", "block.1.attn.qkv.bias": "BF16", "block.1.attn.sinks": "BF16", "block.1.attn.out.weight": "BF16", "block.1.attn.out.bias": "BF16", "block.1.mlp.norm.scale": "BF16", "block.1.mlp.gate.weight": "BF16", "block.1.mlp.gate.bias": "BF16", "block.1.mlp.mlp1_weight.blocks": "FP4", "block.1.mlp.mlp1_weight.scales": "UE8", "block.1.mlp.mlp1_bias": "BF16", "block.1.mlp.mlp2_weight.blocks": "FP4", "block.1.mlp.mlp2_weight.scales": "UE8", "block.1.mlp.mlp2_bias": "BF16", "block.2.attn.norm.scale": "BF16", "block.2.attn.qkv.weight": "BF16", "block.2.attn.qkv.bias": "BF16", "block.2.attn.sinks": "BF16", "block.2.attn.out.weight": "BF16", "block.2.attn.out.bias": "BF16", "block.2.mlp.norm.scale": "BF16", "block.2.mlp.gate.weight": "BF16", "block.2.mlp.gate.bias": "BF16", "block.2.mlp.mlp1_weight.blocks": "FP4", "block.2.mlp.mlp1_weight.scales": "UE8", "block.2.mlp.mlp1_bias": "BF16", "block.2.mlp.mlp2_weight.blocks": "FP4", "block.2.mlp.mlp2_weight.scales": "UE8", "block.2.mlp.mlp2_bias": "BF16", "block.3.attn.norm.scale": "BF16", "block.3.attn.qkv.weight": "BF16", "block.3.attn.qkv.bias": "BF16", "block.3.attn.sinks": "BF16", "block.3.attn.out.weight": "BF16", "block.3.attn.out.bias": "BF16", "block.3.mlp.norm.scale": "BF16", "block.3.mlp.gate.weight": "BF16", "block.3.mlp.gate.bias": "BF16", "block.3.mlp.mlp1_weight.blocks": "FP4", "block.3.mlp.mlp1_weight.scales": "UE8", "block.3.mlp.mlp1_bias": "BF16", "block.3.mlp.mlp2_weight.blocks": "FP4", "block.3.mlp.mlp2_weight.scales": "UE8", "block.3.mlp.mlp2_bias": "BF16", "block.4.attn.norm.scale": "BF16", "block.4.attn.qkv.weight": "BF16", "block.4.attn.qkv.bias": "BF16", "block.4.attn.sinks": "BF16", "block.4.attn.out.weight": "BF16", "block.4.attn.out.bias": "BF16", "block.4.mlp.norm.scale": "BF16", "block.4.mlp.gate.weight": "BF16", "block.4.mlp.gate.bias": "BF16", "block.4.mlp.mlp1_weight.blocks": "FP4", "block.4.mlp.mlp1_weight.scales": "UE8", "block.4.mlp.mlp1_bias": "BF16", "block.4.mlp.mlp2_weight.blocks": "FP4", "block.4.mlp.mlp2_weight.scales": "UE8", "block.4.mlp.mlp2_bias": "BF16", "block.5.attn.norm.scale": "BF16", "block.5.attn.qkv.weight": "BF16", "block.5.attn.qkv.bias": "BF16", "block.5.attn.sinks": "BF16", "block.5.attn.out.weight": "BF16", "block.5.attn.out.bias": "BF16", "block.5.mlp.norm.scale": "BF16", "block.5.mlp.gate.weight": "BF16", "block.5.mlp.gate.bias": "BF16", "block.5.mlp.mlp1_weight.blocks": "FP4", "block.5.mlp.mlp1_weight.scales": "UE8", "block.5.mlp.mlp1_bias": "BF16", "block.5.mlp.mlp2_weight.blocks": "FP4", "block.5.mlp.mlp2_weight.scales": "UE8", "block.5.mlp.mlp2_bias": "BF16", "block.6.attn.norm.scale": "BF16", "block.6.attn.qkv.weight": "BF16", "block.6.attn.qkv.bias": "BF16", "block.6.attn.sinks": "BF16", "block.6.attn.out.weight": "BF16", "block.6.attn.out.bias": "BF16", "block.6.mlp.norm.scale": "BF16", "block.6.mlp.gate.weight": "BF16", "block.6.mlp.gate.bias": "BF16", "block.6.mlp.mlp1_weight.blocks": "FP4", "block.6.mlp.mlp1_weight.scales": "UE8", "block.6.mlp.mlp1_bias": "BF16", "block.6.mlp.mlp2_weight.blocks": "FP4", "block.6.mlp.mlp2_weight.scales": "UE8", "block.6.mlp.mlp2_bias": "BF16", "block.7.attn.norm.scale": "BF16", "block.7.attn.qkv.weight": "BF16", "block.7.attn.qkv.bias": "BF16", "block.7.attn.sinks": "BF16", "block.7.attn.out.weight": "BF16", "block.7.attn.out.bias": "BF16", "block.7.mlp.norm.scale": "BF16", "block.7.mlp.gate.weight": "BF16", "block.7.mlp.gate.bias": "BF16", "block.7.mlp.mlp1_weight.blocks": "FP4", "block.7.mlp.mlp1_weight.scales": "UE8", "block.7.mlp.mlp1_bias": "BF16", "block.7.mlp.mlp2_weight.blocks": "FP4", "block.7.mlp.mlp2_weight.scales": "UE8", "block.7.mlp.mlp2_bias": "BF16", "block.8.attn.norm.scale": "BF16", "block.8.attn.qkv.weight": "BF16", "block.8.attn.qkv.bias": "BF16", "block.8.attn.sinks": "BF16", "block.8.attn.out.weight": "BF16", "block.8.attn.out.bias": "BF16", "block.8.mlp.norm.scale": "BF16", "block.8.mlp.gate.weight": "BF16", "block.8.mlp.gate.bias": "BF16", "block.8.mlp.mlp1_weight.blocks": "FP4", "block.8.mlp.mlp1_weight.scales": "UE8", "block.8.mlp.mlp1_bias": "BF16", "block.8.mlp.mlp2_weight.blocks": "FP4", "block.8.mlp.mlp2_weight.scales": "UE8", "block.8.mlp.mlp2_bias": "BF16", "block.9.attn.norm.scale": "BF16", "block.9.attn.qkv.weight": "BF16", "block.9.attn.qkv.bias": "BF16", "block.9.attn.sinks": "BF16", "block.9.attn.out.weight": "BF16", "block.9.attn.out.bias": "BF16", "block.9.mlp.norm.scale": "BF16", "block.9.mlp.gate.weight": "BF16", "block.9.mlp.gate.bias": "BF16", "block.9.mlp.mlp1_weight.blocks": "FP4", "block.9.mlp.mlp1_weight.scales": "UE8", "block.9.mlp.mlp1_bias": "BF16", "block.9.mlp.mlp2_weight.blocks": "FP4", "block.9.mlp.mlp2_weight.scales": "UE8", "block.9.mlp.mlp2_bias": "BF16", "block.10.attn.norm.scale": "BF16", "block.10.attn.qkv.weight": "BF16", "block.10.attn.qkv.bias": "BF16", "block.10.attn.sinks": "BF16", "block.10.attn.out.weight": "BF16", "block.10.attn.out.bias": "BF16", "block.10.mlp.norm.scale": "BF16", "block.10.mlp.gate.weight": "BF16", "block.10.mlp.gate.bias": "BF16", "block.10.mlp.mlp1_weight.blocks": "FP4", "block.10.mlp.mlp1_weight.scales": "UE8", "block.10.mlp.mlp1_bias": "BF16", "block.10.mlp.mlp2_weight.blocks": "FP4", "block.10.mlp.mlp2_weight.scales": "UE8", "block.10.mlp.mlp2_bias": "BF16", "block.11.attn.norm.scale": "BF16", "block.11.attn.qkv.weight": "BF16", "block.11.attn.qkv.bias": "BF16", "block.11.attn.sinks": "BF16", "block.11.attn.out.weight": "BF16", "block.11.attn.out.bias": "BF16", "block.11.mlp.norm.scale": "BF16", "block.11.mlp.gate.weight": "BF16", "block.11.mlp.gate.bias": "BF16", "block.11.mlp.mlp1_weight.blocks": "FP4", "block.11.mlp.mlp1_weight.scales": "UE8", "block.11.mlp.mlp1_bias": "BF16", "block.11.mlp.mlp2_weight.blocks": "FP4", "block.11.mlp.mlp2_weight.scales": "UE8", "block.11.mlp.mlp2_bias": "BF16", "block.12.attn.norm.scale": "BF16", "block.12.attn.qkv.weight": "BF16", "block.12.attn.qkv.bias": "BF16", "block.12.attn.sinks": "BF16", "block.12.attn.out.weight": "BF16", "block.12.attn.out.bias": "BF16", "block.12.mlp.norm.scale": "BF16", "block.12.mlp.gate.weight": "BF16", "block.12.mlp.gate.bias": "BF16", "block.12.mlp.mlp1_weight.blocks": "FP4", "block.12.mlp.mlp1_weight.scales": "UE8", "block.12.mlp.mlp1_bias": "BF16", "block.12.mlp.mlp2_weight.blocks": "FP4", "block.12.mlp.mlp2_weight.scales": "UE8", "block.12.mlp.mlp2_bias": "BF16", "block.13.attn.norm.scale": "BF16", "block.13.attn.qkv.weight": "BF16", "block.13.attn.qkv.bias": "BF16", "block.13.attn.sinks": "BF16", "block.13.attn.out.weight": "BF16", "block.13.attn.out.bias": "BF16", "block.13.mlp.norm.scale": "BF16", "block.13.mlp.gate.weight": "BF16", "block.13.mlp.gate.bias": "BF16", "block.13.mlp.mlp1_weight.blocks": "FP4", "block.13.mlp.mlp1_weight.scales": "UE8", "block.13.mlp.mlp1_bias": "BF16", "block.13.mlp.mlp2_weight.blocks": "FP4", "block.13.mlp.mlp2_weight.scales": "UE8", "block.13.mlp.mlp2_bias": "BF16", "block.14.attn.norm.scale": "BF16", "block.14.attn.qkv.weight": "BF16", "block.14.attn.qkv.bias": "BF16", "block.14.attn.sinks": "BF16", "block.14.attn.out.weight": "BF16", "block.14.attn.out.bias": "BF16", "block.14.mlp.norm.scale": "BF16", "block.14.mlp.gate.weight": "BF16", "block.14.mlp.gate.bias": "BF16", "block.14.mlp.mlp1_weight.blocks": "FP4", "block.14.mlp.mlp1_weight.scales": "UE8", "block.14.mlp.mlp1_bias": "BF16", "block.14.mlp.mlp2_weight.blocks": "FP4", "block.14.mlp.mlp2_weight.scales": "UE8", "block.14.mlp.mlp2_bias": "BF16", "block.15.attn.norm.scale": "BF16", "block.15.attn.qkv.weight": "BF16", "block.15.attn.qkv.bias": "BF16", "block.15.attn.sinks": "BF16", "block.15.attn.out.weight": "BF16", "block.15.attn.out.bias": "BF16", "block.15.mlp.norm.scale": "BF16", "block.15.mlp.gate.weight": "BF16", "block.15.mlp.gate.bias": "BF16", "block.15.mlp.mlp1_weight.blocks": "FP4", "block.15.mlp.mlp1_weight.scales": "UE8", "block.15.mlp.mlp1_bias": "BF16", "block.15.mlp.mlp2_weight.blocks": "FP4", "block.15.mlp.mlp2_weight.scales": "UE8", "block.15.mlp.mlp2_bias": "BF16", "block.16.attn.norm.scale": "BF16", "block.16.attn.qkv.weight": "BF16", "block.16.attn.qkv.bias": "BF16", "block.16.attn.sinks": "BF16", "block.16.attn.out.weight": "BF16", "block.16.attn.out.bias": "BF16", "block.16.mlp.norm.scale": "BF16", "block.16.mlp.gate.weight": "BF16", "block.16.mlp.gate.bias": "BF16", "block.16.mlp.mlp1_weight.blocks": "FP4", "block.16.mlp.mlp1_weight.scales": "UE8", "block.16.mlp.mlp1_bias": "BF16", "block.16.mlp.mlp2_weight.blocks": "FP4", "block.16.mlp.mlp2_weight.scales": "UE8", "block.16.mlp.mlp2_bias": "BF16", "block.17.attn.norm.scale": "BF16", "block.17.attn.qkv.weight": "BF16", "block.17.attn.qkv.bias": "BF16", "block.17.attn.sinks": "BF16", "block.17.attn.out.weight": "BF16", "block.17.attn.out.bias": "BF16", "block.17.mlp.norm.scale": "BF16", "block.17.mlp.gate.weight": "BF16", "block.17.mlp.gate.bias": "BF16", "block.17.mlp.mlp1_weight.blocks": "FP4", "block.17.mlp.mlp1_weight.scales": "UE8", "block.17.mlp.mlp1_bias": "BF16", "block.17.mlp.mlp2_weight.blocks": "FP4", "block.17.mlp.mlp2_weight.scales": "UE8", "block.17.mlp.mlp2_bias": "BF16", "block.18.attn.norm.scale": "BF16", "block.18.attn.qkv.weight": "BF16", "block.18.attn.qkv.bias": "BF16", "block.18.attn.sinks": "BF16", "block.18.attn.out.weight": "BF16", "block.18.attn.out.bias": "BF16", "block.18.mlp.norm.scale": "BF16", "block.18.mlp.gate.weight": "BF16", "block.18.mlp.gate.bias": "BF16", "block.18.mlp.mlp1_weight.blocks": "FP4", "block.18.mlp.mlp1_weight.scales": "UE8", "block.18.mlp.mlp1_bias": "BF16", "block.18.mlp.mlp2_weight.blocks": "FP4", "block.18.mlp.mlp2_weight.scales": "UE8", "block.18.mlp.mlp2_bias": "BF16", "block.19.attn.norm.scale": "BF16", "block.19.attn.qkv.weight": "BF16", "block.19.attn.qkv.bias": "BF16", "block.19.attn.sinks": "BF16", "block.19.attn.out.weight": "BF16", "block.19.attn.out.bias": "BF16", "block.19.mlp.norm.scale": "BF16", "block.19.mlp.gate.weight": "BF16", "block.19.mlp.gate.bias": "BF16", "block.19.mlp.mlp1_weight.blocks": "FP4", "block.19.mlp.mlp1_weight.scales": "UE8", "block.19.mlp.mlp1_bias": "BF16", "block.19.mlp.mlp2_weight.blocks": "FP4", "block.19.mlp.mlp2_weight.scales": "UE8", "block.19.mlp.mlp2_bias": "BF16", "block.20.attn.norm.scale": "BF16", "block.20.attn.qkv.weight": "BF16", "block.20.attn.qkv.bias": "BF16", "block.20.attn.sinks": "BF16", "block.20.attn.out.weight": "BF16", "block.20.attn.out.bias": "BF16", "block.20.mlp.norm.scale": "BF16", "block.20.mlp.gate.weight": "BF16", "block.20.mlp.gate.bias": "BF16", "block.20.mlp.mlp1_weight.blocks": "FP4", "block.20.mlp.mlp1_weight.scales": "UE8", "block.20.mlp.mlp1_bias": "BF16", "block.20.mlp.mlp2_weight.blocks": "FP4", "block.20.mlp.mlp2_weight.scales": "UE8", "block.20.mlp.mlp2_bias": "BF16", "block.21.attn.norm.scale": "BF16", "block.21.attn.qkv.weight": "BF16", "block.21.attn.qkv.bias": "BF16", "block.21.attn.sinks": "BF16", "block.21.attn.out.weight": "BF16", "block.21.attn.out.bias": "BF16", "block.21.mlp.norm.scale": "BF16", "block.21.mlp.gate.weight": "BF16", "block.21.mlp.gate.bias": "BF16", "block.21.mlp.mlp1_weight.blocks": "FP4", "block.21.mlp.mlp1_weight.scales": "UE8", "block.21.mlp.mlp1_bias": "BF16", "block.21.mlp.mlp2_weight.blocks": "FP4", "block.21.mlp.mlp2_weight.scales": "UE8", "block.21.mlp.mlp2_bias": "BF16", "block.22.attn.norm.scale": "BF16", "block.22.attn.qkv.weight": "BF16", "block.22.attn.qkv.bias": "BF16", "block.22.attn.sinks": "BF16", "block.22.attn.out.weight": "BF16", "block.22.attn.out.bias": "BF16", "block.22.mlp.norm.scale": "BF16", "block.22.mlp.gate.weight": "BF16", "block.22.mlp.gate.bias": "BF16", "block.22.mlp.mlp1_weight.blocks": "FP4", "block.22.mlp.mlp1_weight.scales": "UE8", "block.22.mlp.mlp1_bias": "BF16", "block.22.mlp.mlp2_weight.blocks": "FP4", "block.22.mlp.mlp2_weight.scales": "UE8", "block.22.mlp.mlp2_bias": "BF16", "block.23.attn.norm.scale": "BF16", "block.23.attn.qkv.weight": "BF16", "block.23.attn.qkv.bias": "BF16", "block.23.attn.sinks": "BF16", "block.23.attn.out.weight": "BF16", "block.23.attn.out.bias": "BF16", "block.23.mlp.norm.scale": "BF16", "block.23.mlp.gate.weight": "BF16", "block.23.mlp.gate.bias": "BF16", "block.23.mlp.mlp1_weight.blocks": "FP4", "block.23.mlp.mlp1_weight.scales": "UE8", "block.23.mlp.mlp1_bias": "BF16", "block.23.mlp.mlp2_weight.blocks": "FP4", "block.23.mlp.mlp2_weight.scales": "UE8", "block.23.mlp.mlp2_bias": "BF16", "block.24.attn.norm.scale": "BF16", "block.24.attn.qkv.weight": "BF16", "block.24.attn.qkv.bias": "BF16", "block.24.attn.sinks": "BF16", "block.24.attn.out.weight": "BF16", "block.24.attn.out.bias": "BF16", "block.24.mlp.norm.scale": "BF16", "block.24.mlp.gate.weight": "BF16", "block.24.mlp.gate.bias": "BF16", "block.24.mlp.mlp1_weight.blocks": "FP4", "block.24.mlp.mlp1_weight.scales": "UE8", "block.24.mlp.mlp1_bias": "BF16", "block.24.mlp.mlp2_weight.blocks": "FP4", "block.24.mlp.mlp2_weight.scales": "UE8", "block.24.mlp.mlp2_bias": "BF16", "block.25.attn.norm.scale": "BF16", "block.25.attn.qkv.weight": "BF16", "block.25.attn.qkv.bias": "BF16", "block.25.attn.sinks": "BF16", "block.25.attn.out.weight": "BF16", "block.25.attn.out.bias": "BF16", "block.25.mlp.norm.scale": "BF16", "block.25.mlp.gate.weight": "BF16", "block.25.mlp.gate.bias": "BF16", "block.25.mlp.mlp1_weight.blocks": "FP4", "block.25.mlp.mlp1_weight.scales": "UE8", "block.25.mlp.mlp1_bias": "BF16", "block.25.mlp.mlp2_weight.blocks": "FP4", "block.25.mlp.mlp2_weight.scales": "UE8", "block.25.mlp.mlp2_bias": "BF16", "block.26.attn.norm.scale": "BF16", "block.26.attn.qkv.weight": "BF16", "block.26.attn.qkv.bias": "BF16", "block.26.attn.sinks": "BF16", "block.26.attn.out.weight": "BF16", "block.26.attn.out.bias": "BF16", "block.26.mlp.norm.scale": "BF16", "block.26.mlp.gate.weight": "BF16", "block.26.mlp.gate.bias": "BF16", "block.26.mlp.mlp1_weight.blocks": "FP4", "block.26.mlp.mlp1_weight.scales": "UE8", "block.26.mlp.mlp1_bias": "BF16", "block.26.mlp.mlp2_weight.blocks": "FP4", "block.26.mlp.mlp2_weight.scales": "UE8", "block.26.mlp.mlp2_bias": "BF16", "block.27.attn.norm.scale": "BF16", "block.27.attn.qkv.weight": "BF16", "block.27.attn.qkv.bias": "BF16", "block.27.attn.sinks": "BF16", "block.27.attn.out.weight": "BF16", "block.27.attn.out.bias": "BF16", "block.27.mlp.norm.scale": "BF16", "block.27.mlp.gate.weight": "BF16", "block.27.mlp.gate.bias": "BF16", "block.27.mlp.mlp1_weight.blocks": "FP4", "block.27.mlp.mlp1_weight.scales": "UE8", "block.27.mlp.mlp1_bias": "BF16", "block.27.mlp.mlp2_weight.blocks": "FP4", "block.27.mlp.mlp2_weight.scales": "UE8", "block.27.mlp.mlp2_bias": "BF16", "block.28.attn.norm.scale": "BF16", "block.28.attn.qkv.weight": "BF16", "block.28.attn.qkv.bias": "BF16", "block.28.attn.sinks": "BF16", "block.28.attn.out.weight": "BF16", "block.28.attn.out.bias": "BF16", "block.28.mlp.norm.scale": "BF16", "block.28.mlp.gate.weight": "BF16", "block.28.mlp.gate.bias": "BF16", "block.28.mlp.mlp1_weight.blocks": "FP4", "block.28.mlp.mlp1_weight.scales": "UE8", "block.28.mlp.mlp1_bias": "BF16", "block.28.mlp.mlp2_weight.blocks": "FP4", "block.28.mlp.mlp2_weight.scales": "UE8", "block.28.mlp.mlp2_bias": "BF16", "block.29.attn.norm.scale": "BF16", "block.29.attn.qkv.weight": "BF16", "block.29.attn.qkv.bias": "BF16", "block.29.attn.sinks": "BF16", "block.29.attn.out.weight": "BF16", "block.29.attn.out.bias": "BF16", "block.29.mlp.norm.scale": "BF16", "block.29.mlp.gate.weight": "BF16", "block.29.mlp.gate.bias": "BF16", "block.29.mlp.mlp1_weight.blocks": "FP4", "block.29.mlp.mlp1_weight.scales": "UE8", "block.29.mlp.mlp1_bias": "BF16", "block.29.mlp.mlp2_weight.blocks": "FP4", "block.29.mlp.mlp2_weight.scales": "UE8", "block.29.mlp.mlp2_bias": "BF16", "block.30.attn.norm.scale": "BF16", "block.30.attn.qkv.weight": "BF16", "block.30.attn.qkv.bias": "BF16", "block.30.attn.sinks": "BF16", "block.30.attn.out.weight": "BF16", "block.30.attn.out.bias": "BF16", "block.30.mlp.norm.scale": "BF16", "block.30.mlp.gate.weight": "BF16", "block.30.mlp.gate.bias": "BF16", "block.30.mlp.mlp1_weight.blocks": "FP4", "block.30.mlp.mlp1_weight.scales": "UE8", "block.30.mlp.mlp1_bias": "BF16", "block.30.mlp.mlp2_weight.blocks": "FP4", "block.30.mlp.mlp2_weight.scales": "UE8", "block.30.mlp.mlp2_bias": "BF16", "block.31.attn.norm.scale": "BF16", "block.31.attn.qkv.weight": "BF16", "block.31.attn.qkv.bias": "BF16", "block.31.attn.sinks": "BF16", "block.31.attn.out.weight": "BF16", "block.31.attn.out.bias": "BF16", "block.31.mlp.norm.scale": "BF16", "block.31.mlp.gate.weight": "BF16", "block.31.mlp.gate.bias": "BF16", "block.31.mlp.mlp1_weight.blocks": "FP4", "block.31.mlp.mlp1_weight.scales": "UE8", "block.31.mlp.mlp1_bias": "BF16", "block.31.mlp.mlp2_weight.blocks": "FP4", "block.31.mlp.mlp2_weight.scales": "UE8", "block.31.mlp.mlp2_bias": "BF16", "block.32.attn.norm.scale": "BF16", "block.32.attn.qkv.weight": "BF16", "block.32.attn.qkv.bias": "BF16", "block.32.attn.sinks": "BF16", "block.32.attn.out.weight": "BF16", "block.32.attn.out.bias": "BF16", "block.32.mlp.norm.scale": "BF16", "block.32.mlp.gate.weight": "BF16", "block.32.mlp.gate.bias": "BF16", "block.32.mlp.mlp1_weight.blocks": "FP4", "block.32.mlp.mlp1_weight.scales": "UE8", "block.32.mlp.mlp1_bias": "BF16", "block.32.mlp.mlp2_weight.blocks": "FP4", "block.32.mlp.mlp2_weight.scales": "UE8", "block.32.mlp.mlp2_bias": "BF16", "block.33.attn.norm.scale": "BF16", "block.33.attn.qkv.weight": "BF16", "block.33.attn.qkv.bias": "BF16", "block.33.attn.sinks": "BF16", "block.33.attn.out.weight": "BF16", "block.33.attn.out.bias": "BF16", "block.33.mlp.norm.scale": "BF16", "block.33.mlp.gate.weight": "BF16", "block.33.mlp.gate.bias": "BF16", "block.33.mlp.mlp1_weight.blocks": "FP4", "block.33.mlp.mlp1_weight.scales": "UE8", "block.33.mlp.mlp1_bias": "BF16", "block.33.mlp.mlp2_weight.blocks": "FP4", "block.33.mlp.mlp2_weight.scales": "UE8", "block.33.mlp.mlp2_bias": "BF16", "block.34.attn.norm.scale": "BF16", "block.34.attn.qkv.weight": "BF16", "block.34.attn.qkv.bias": "BF16", "block.34.attn.sinks": "BF16", "block.34.attn.out.weight": "BF16", "block.34.attn.out.bias": "BF16", "block.34.mlp.norm.scale": "BF16", "block.34.mlp.gate.weight": "BF16", "block.34.mlp.gate.bias": "BF16", "block.34.mlp.mlp1_weight.blocks": "FP4", "block.34.mlp.mlp1_weight.scales": "UE8", "block.34.mlp.mlp1_bias": "BF16", "block.34.mlp.mlp2_weight.blocks": "FP4", "block.34.mlp.mlp2_weight.scales": "UE8", "block.34.mlp.mlp2_bias": "BF16", "block.35.attn.norm.scale": "BF16", "block.35.attn.qkv.weight": "BF16", "block.35.attn.qkv.bias": "BF16", "block.35.attn.sinks": "BF16", "block.35.attn.out.weight": "BF16", "block.35.attn.out.bias": "BF16", "block.35.mlp.norm.scale": "BF16", "block.35.mlp.gate.weight": "BF16", "block.35.mlp.gate.bias": "BF16", "block.35.mlp.mlp1_weight.blocks": "FP4", "block.35.mlp.mlp1_weight.scales": "UE8", "block.35.mlp.mlp1_bias": "BF16", "block.35.mlp.mlp2_weight.blocks": "FP4", "block.35.mlp.mlp2_weight.scales": "UE8", "block.35.mlp.mlp2_bias": "BF16", "norm.scale": "BF16", "unembedding.weight": "BF16"}

generation_config.json

@@ -1,11 +0,0 @@
-{
-  "bos_token_id": 199998,
-  "do_sample": true,
-  "eos_token_id": [
-    200002,
-    199999,
-    200012
-  ],
-  "pad_token_id": 199999,
-  "transformers_version": "4.55.0.dev0"
-}

model.safetensors.index.json

@@ -1,550 +0,0 @@
-{
-  "metadata": {
-    "total_size": 65248815744
-  },
-  "weight_map": {
-    "block.0.attn.norm.scale": "model--00001-of-00007.safetensors",
-    "block.0.attn.out.bias": "model--00001-of-00007.safetensors",
-    "block.0.attn.out.weight": "model--00001-of-00007.safetensors",
-    "block.0.attn.qkv.bias": "model--00001-of-00007.safetensors",
-    "block.0.attn.qkv.weight": "model--00001-of-00007.safetensors",
-    "block.0.attn.sinks": "model--00001-of-00007.safetensors",
-    "block.0.mlp.gate.bias": "model--00001-of-00007.safetensors",
-    "block.0.mlp.gate.weight": "model--00001-of-00007.safetensors",
-    "block.0.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
-    "block.0.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.0.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
-    "block.0.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
-    "block.0.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.0.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
-    "block.0.mlp.norm.scale": "model--00001-of-00007.safetensors",
-    "block.1.attn.norm.scale": "model--00001-of-00007.safetensors",
-    "block.1.attn.out.bias": "model--00001-of-00007.safetensors",
-    "block.1.attn.out.weight": "model--00001-of-00007.safetensors",
-    "block.1.attn.qkv.bias": "model--00001-of-00007.safetensors",
-    "block.1.attn.qkv.weight": "model--00001-of-00007.safetensors",
-    "block.1.attn.sinks": "model--00001-of-00007.safetensors",
-    "block.1.mlp.gate.bias": "model--00001-of-00007.safetensors",
-    "block.1.mlp.gate.weight": "model--00001-of-00007.safetensors",
-    "block.1.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
-    "block.1.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.1.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
-    "block.1.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
-    "block.1.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.1.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
-    "block.1.mlp.norm.scale": "model--00001-of-00007.safetensors",
-    "block.10.attn.norm.scale": "model--00001-of-00007.safetensors",
-    "block.10.attn.out.bias": "model--00001-of-00007.safetensors",
-    "block.10.attn.out.weight": "model--00001-of-00007.safetensors",
-    "block.10.attn.qkv.bias": "model--00001-of-00007.safetensors",
-    "block.10.attn.qkv.weight": "model--00001-of-00007.safetensors",
-    "block.10.attn.sinks": "model--00001-of-00007.safetensors",
-    "block.10.mlp.gate.bias": "model--00001-of-00007.safetensors",
-    "block.10.mlp.gate.weight": "model--00001-of-00007.safetensors",
-    "block.10.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
-    "block.10.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.10.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
-    "block.10.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
-    "block.10.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.10.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
-    "block.10.mlp.norm.scale": "model--00001-of-00007.safetensors",
-    "block.11.attn.norm.scale": "model--00001-of-00007.safetensors",
-    "block.11.attn.out.bias": "model--00001-of-00007.safetensors",
-    "block.11.attn.out.weight": "model--00001-of-00007.safetensors",
-    "block.11.attn.qkv.bias": "model--00001-of-00007.safetensors",
-    "block.11.attn.qkv.weight": "model--00001-of-00007.safetensors",
-    "block.11.attn.sinks": "model--00001-of-00007.safetensors",
-    "block.11.mlp.gate.bias": "model--00001-of-00007.safetensors",
-    "block.11.mlp.gate.weight": "model--00001-of-00007.safetensors",
-    "block.11.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
-    "block.11.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.11.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
-    "block.11.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
-    "block.11.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.11.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
-    "block.11.mlp.norm.scale": "model--00001-of-00007.safetensors",
-    "block.12.attn.norm.scale": "model--00001-of-00007.safetensors",
-    "block.12.attn.out.bias": "model--00001-of-00007.safetensors",
-    "block.12.attn.out.weight": "model--00001-of-00007.safetensors",
-    "block.12.attn.qkv.bias": "model--00001-of-00007.safetensors",
-    "block.12.attn.qkv.weight": "model--00001-of-00007.safetensors",
-    "block.12.attn.sinks": "model--00001-of-00007.safetensors",
-    "block.12.mlp.gate.bias": "model--00001-of-00007.safetensors",
-    "block.12.mlp.gate.weight": "model--00001-of-00007.safetensors",
-    "block.12.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
-    "block.12.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.12.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
-    "block.12.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
-    "block.12.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.12.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
-    "block.12.mlp.norm.scale": "model--00001-of-00007.safetensors",
-    "block.13.attn.norm.scale": "model--00001-of-00007.safetensors",
-    "block.13.attn.out.bias": "model--00001-of-00007.safetensors",
-    "block.13.attn.out.weight": "model--00001-of-00007.safetensors",
-    "block.13.attn.qkv.bias": "model--00001-of-00007.safetensors",
-    "block.13.attn.qkv.weight": "model--00001-of-00007.safetensors",
-    "block.13.attn.sinks": "model--00001-of-00007.safetensors",
-    "block.13.mlp.gate.bias": "model--00001-of-00007.safetensors",
-    "block.13.mlp.gate.weight": "model--00001-of-00007.safetensors",
-    "block.13.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
-    "block.13.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.13.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
-    "block.13.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
-    "block.13.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
-    "block.13.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
-    "block.13.mlp.norm.scale": "model--00001-of-00007.safetensors",
-    "block.14.attn.norm.scale": "model--00001-of-00007.safetensors",
-    "block.14.attn.out.bias": "model--00001-of-00007.safetensors",
-    "block.14.attn.out.weight": "model--00001-of-00007.safetensors",
-    "block.14.attn.qkv.bias": "model--00001-of-00007.safetensors",
-    "block.14.attn.qkv.weight": "model--00001-of-00007.safetensors",
-    "block.14.attn.sinks": "model--00001-of-00007.safetensors",
-    "block.14.mlp.gate.bias": "model--00001-of-00007.safetensors",
-    "block.14.mlp.gate.weight": "model--00001-of-00007.safetensors",
-    "block.14.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
-    "block.14.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.14.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
-    "block.14.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
-    "block.14.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.14.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
-    "block.14.mlp.norm.scale": "model--00002-of-00007.safetensors",
-    "block.15.attn.norm.scale": "model--00002-of-00007.safetensors",
-    "block.15.attn.out.bias": "model--00002-of-00007.safetensors",
-    "block.15.attn.out.weight": "model--00002-of-00007.safetensors",
-    "block.15.attn.qkv.bias": "model--00002-of-00007.safetensors",
-    "block.15.attn.qkv.weight": "model--00002-of-00007.safetensors",
-    "block.15.attn.sinks": "model--00002-of-00007.safetensors",
-    "block.15.mlp.gate.bias": "model--00002-of-00007.safetensors",
-    "block.15.mlp.gate.weight": "model--00002-of-00007.safetensors",
-    "block.15.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
-    "block.15.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.15.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
-    "block.15.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
-    "block.15.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.15.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
-    "block.15.mlp.norm.scale": "model--00002-of-00007.safetensors",
-    "block.16.attn.norm.scale": "model--00002-of-00007.safetensors",
-    "block.16.attn.out.bias": "model--00002-of-00007.safetensors",
-    "block.16.attn.out.weight": "model--00002-of-00007.safetensors",
-    "block.16.attn.qkv.bias": "model--00002-of-00007.safetensors",
-    "block.16.attn.qkv.weight": "model--00002-of-00007.safetensors",
-    "block.16.attn.sinks": "model--00002-of-00007.safetensors",
-    "block.16.mlp.gate.bias": "model--00002-of-00007.safetensors",
-    "block.16.mlp.gate.weight": "model--00002-of-00007.safetensors",
-    "block.16.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
-    "block.16.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.16.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
-    "block.16.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
-    "block.16.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.16.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
-    "block.16.mlp.norm.scale": "model--00002-of-00007.safetensors",
-    "block.17.attn.norm.scale": "model--00002-of-00007.safetensors",
-    "block.17.attn.out.bias": "model--00002-of-00007.safetensors",
-    "block.17.attn.out.weight": "model--00002-of-00007.safetensors",
-    "block.17.attn.qkv.bias": "model--00002-of-00007.safetensors",
-    "block.17.attn.qkv.weight": "model--00002-of-00007.safetensors",
-    "block.17.attn.sinks": "model--00002-of-00007.safetensors",
-    "block.17.mlp.gate.bias": "model--00002-of-00007.safetensors",
-    "block.17.mlp.gate.weight": "model--00002-of-00007.safetensors",
-    "block.17.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
-    "block.17.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.17.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
-    "block.17.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
-    "block.17.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.17.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
-    "block.17.mlp.norm.scale": "model--00002-of-00007.safetensors",
-    "block.18.attn.norm.scale": "model--00002-of-00007.safetensors",
-    "block.18.attn.out.bias": "model--00002-of-00007.safetensors",
-    "block.18.attn.out.weight": "model--00002-of-00007.safetensors",
-    "block.18.attn.qkv.bias": "model--00002-of-00007.safetensors",
-    "block.18.attn.qkv.weight": "model--00002-of-00007.safetensors",
-    "block.18.attn.sinks": "model--00002-of-00007.safetensors",
-    "block.18.mlp.gate.bias": "model--00002-of-00007.safetensors",
-    "block.18.mlp.gate.weight": "model--00002-of-00007.safetensors",
-    "block.18.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
-    "block.18.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.18.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
-    "block.18.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
-    "block.18.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.18.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
-    "block.18.mlp.norm.scale": "model--00002-of-00007.safetensors",
-    "block.19.attn.norm.scale": "model--00002-of-00007.safetensors",
-    "block.19.attn.out.bias": "model--00002-of-00007.safetensors",
-    "block.19.attn.out.weight": "model--00002-of-00007.safetensors",
-    "block.19.attn.qkv.bias": "model--00002-of-00007.safetensors",
-    "block.19.attn.qkv.weight": "model--00002-of-00007.safetensors",
-    "block.19.attn.sinks": "model--00002-of-00007.safetensors",
-    "block.19.mlp.gate.bias": "model--00002-of-00007.safetensors",
-    "block.19.mlp.gate.weight": "model--00002-of-00007.safetensors",
-    "block.19.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
-    "block.19.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.19.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
-    "block.19.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
-    "block.19.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
-    "block.19.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
-    "block.19.mlp.norm.scale": "model--00002-of-00007.safetensors",
-    "block.2.attn.norm.scale": "model--00002-of-00007.safetensors",
-    "block.2.attn.out.bias": "model--00002-of-00007.safetensors",
-    "block.2.attn.out.weight": "model--00002-of-00007.safetensors",
-    "block.2.attn.qkv.bias": "model--00002-of-00007.safetensors",
-    "block.2.attn.qkv.weight": "model--00002-of-00007.safetensors",
-    "block.2.attn.sinks": "model--00002-of-00007.safetensors",
-    "block.2.mlp.gate.bias": "model--00002-of-00007.safetensors",
-    "block.2.mlp.gate.weight": "model--00002-of-00007.safetensors",
-    "block.2.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
-    "block.2.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.2.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
-    "block.2.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
-    "block.2.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.2.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
-    "block.2.mlp.norm.scale": "model--00003-of-00007.safetensors",
-    "block.20.attn.norm.scale": "model--00003-of-00007.safetensors",
-    "block.20.attn.out.bias": "model--00003-of-00007.safetensors",
-    "block.20.attn.out.weight": "model--00003-of-00007.safetensors",
-    "block.20.attn.qkv.bias": "model--00003-of-00007.safetensors",
-    "block.20.attn.qkv.weight": "model--00003-of-00007.safetensors",
-    "block.20.attn.sinks": "model--00003-of-00007.safetensors",
-    "block.20.mlp.gate.bias": "model--00003-of-00007.safetensors",
-    "block.20.mlp.gate.weight": "model--00003-of-00007.safetensors",
-    "block.20.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
-    "block.20.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.20.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
-    "block.20.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
-    "block.20.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.20.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
-    "block.20.mlp.norm.scale": "model--00003-of-00007.safetensors",
-    "block.21.attn.norm.scale": "model--00003-of-00007.safetensors",
-    "block.21.attn.out.bias": "model--00003-of-00007.safetensors",
-    "block.21.attn.out.weight": "model--00003-of-00007.safetensors",
-    "block.21.attn.qkv.bias": "model--00003-of-00007.safetensors",
-    "block.21.attn.qkv.weight": "model--00003-of-00007.safetensors",
-    "block.21.attn.sinks": "model--00003-of-00007.safetensors",
-    "block.21.mlp.gate.bias": "model--00003-of-00007.safetensors",
-    "block.21.mlp.gate.weight": "model--00003-of-00007.safetensors",
-    "block.21.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
-    "block.21.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.21.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
-    "block.21.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
-    "block.21.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.21.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
-    "block.21.mlp.norm.scale": "model--00003-of-00007.safetensors",
-    "block.22.attn.norm.scale": "model--00003-of-00007.safetensors",
-    "block.22.attn.out.bias": "model--00003-of-00007.safetensors",
-    "block.22.attn.out.weight": "model--00003-of-00007.safetensors",
-    "block.22.attn.qkv.bias": "model--00003-of-00007.safetensors",
-    "block.22.attn.qkv.weight": "model--00003-of-00007.safetensors",
-    "block.22.attn.sinks": "model--00003-of-00007.safetensors",
-    "block.22.mlp.gate.bias": "model--00003-of-00007.safetensors",
-    "block.22.mlp.gate.weight": "model--00003-of-00007.safetensors",
-    "block.22.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
-    "block.22.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.22.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
-    "block.22.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
-    "block.22.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.22.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
-    "block.22.mlp.norm.scale": "model--00003-of-00007.safetensors",
-    "block.23.attn.norm.scale": "model--00003-of-00007.safetensors",
-    "block.23.attn.out.bias": "model--00003-of-00007.safetensors",
-    "block.23.attn.out.weight": "model--00003-of-00007.safetensors",
-    "block.23.attn.qkv.bias": "model--00003-of-00007.safetensors",
-    "block.23.attn.qkv.weight": "model--00003-of-00007.safetensors",
-    "block.23.attn.sinks": "model--00003-of-00007.safetensors",
-    "block.23.mlp.gate.bias": "model--00003-of-00007.safetensors",
-    "block.23.mlp.gate.weight": "model--00003-of-00007.safetensors",
-    "block.23.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
-    "block.23.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.23.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
-    "block.23.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
-    "block.23.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.23.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
-    "block.23.mlp.norm.scale": "model--00003-of-00007.safetensors",
-    "block.24.attn.norm.scale": "model--00003-of-00007.safetensors",
-    "block.24.attn.out.bias": "model--00003-of-00007.safetensors",
-    "block.24.attn.out.weight": "model--00003-of-00007.safetensors",
-    "block.24.attn.qkv.bias": "model--00003-of-00007.safetensors",
-    "block.24.attn.qkv.weight": "model--00003-of-00007.safetensors",
-    "block.24.attn.sinks": "model--00003-of-00007.safetensors",
-    "block.24.mlp.gate.bias": "model--00003-of-00007.safetensors",
-    "block.24.mlp.gate.weight": "model--00003-of-00007.safetensors",
-    "block.24.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
-    "block.24.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.24.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
-    "block.24.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
-    "block.24.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
-    "block.24.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
-    "block.24.mlp.norm.scale": "model--00003-of-00007.safetensors",
-    "block.25.attn.norm.scale": "model--00003-of-00007.safetensors",
-    "block.25.attn.out.bias": "model--00003-of-00007.safetensors",
-    "block.25.attn.out.weight": "model--00003-of-00007.safetensors",
-    "block.25.attn.qkv.bias": "model--00003-of-00007.safetensors",
-    "block.25.attn.qkv.weight": "model--00003-of-00007.safetensors",
-    "block.25.attn.sinks": "model--00003-of-00007.safetensors",
-    "block.25.mlp.gate.bias": "model--00003-of-00007.safetensors",
-    "block.25.mlp.gate.weight": "model--00003-of-00007.safetensors",
-    "block.25.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
-    "block.25.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.25.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
-    "block.25.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
-    "block.25.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.25.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
-    "block.25.mlp.norm.scale": "model--00004-of-00007.safetensors",
-    "block.26.attn.norm.scale": "model--00004-of-00007.safetensors",
-    "block.26.attn.out.bias": "model--00004-of-00007.safetensors",
-    "block.26.attn.out.weight": "model--00004-of-00007.safetensors",
-    "block.26.attn.qkv.bias": "model--00004-of-00007.safetensors",
-    "block.26.attn.qkv.weight": "model--00004-of-00007.safetensors",
-    "block.26.attn.sinks": "model--00004-of-00007.safetensors",
-    "block.26.mlp.gate.bias": "model--00004-of-00007.safetensors",
-    "block.26.mlp.gate.weight": "model--00004-of-00007.safetensors",
-    "block.26.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
-    "block.26.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.26.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
-    "block.26.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
-    "block.26.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.26.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
-    "block.26.mlp.norm.scale": "model--00004-of-00007.safetensors",
-    "block.27.attn.norm.scale": "model--00004-of-00007.safetensors",
-    "block.27.attn.out.bias": "model--00004-of-00007.safetensors",
-    "block.27.attn.out.weight": "model--00004-of-00007.safetensors",
-    "block.27.attn.qkv.bias": "model--00004-of-00007.safetensors",
-    "block.27.attn.qkv.weight": "model--00004-of-00007.safetensors",
-    "block.27.attn.sinks": "model--00004-of-00007.safetensors",
-    "block.27.mlp.gate.bias": "model--00004-of-00007.safetensors",
-    "block.27.mlp.gate.weight": "model--00004-of-00007.safetensors",
-    "block.27.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
-    "block.27.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.27.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
-    "block.27.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
-    "block.27.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.27.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
-    "block.27.mlp.norm.scale": "model--00004-of-00007.safetensors",
-    "block.28.attn.norm.scale": "model--00004-of-00007.safetensors",
-    "block.28.attn.out.bias": "model--00004-of-00007.safetensors",
-    "block.28.attn.out.weight": "model--00004-of-00007.safetensors",
-    "block.28.attn.qkv.bias": "model--00004-of-00007.safetensors",
-    "block.28.attn.qkv.weight": "model--00004-of-00007.safetensors",
-    "block.28.attn.sinks": "model--00004-of-00007.safetensors",
-    "block.28.mlp.gate.bias": "model--00004-of-00007.safetensors",
-    "block.28.mlp.gate.weight": "model--00004-of-00007.safetensors",
-    "block.28.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
-    "block.28.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.28.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
-    "block.28.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
-    "block.28.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.28.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
-    "block.28.mlp.norm.scale": "model--00004-of-00007.safetensors",
-    "block.29.attn.norm.scale": "model--00004-of-00007.safetensors",
-    "block.29.attn.out.bias": "model--00004-of-00007.safetensors",
-    "block.29.attn.out.weight": "model--00004-of-00007.safetensors",
-    "block.29.attn.qkv.bias": "model--00004-of-00007.safetensors",
-    "block.29.attn.qkv.weight": "model--00004-of-00007.safetensors",
-    "block.29.attn.sinks": "model--00004-of-00007.safetensors",
-    "block.29.mlp.gate.bias": "model--00004-of-00007.safetensors",
-    "block.29.mlp.gate.weight": "model--00004-of-00007.safetensors",
-    "block.29.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
-    "block.29.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.29.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
-    "block.29.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
-    "block.29.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.29.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
-    "block.29.mlp.norm.scale": "model--00004-of-00007.safetensors",
-    "block.3.attn.norm.scale": "model--00004-of-00007.safetensors",
-    "block.3.attn.out.bias": "model--00004-of-00007.safetensors",
-    "block.3.attn.out.weight": "model--00004-of-00007.safetensors",
-    "block.3.attn.qkv.bias": "model--00004-of-00007.safetensors",
-    "block.3.attn.qkv.weight": "model--00004-of-00007.safetensors",
-    "block.3.attn.sinks": "model--00004-of-00007.safetensors",
-    "block.3.mlp.gate.bias": "model--00004-of-00007.safetensors",
-    "block.3.mlp.gate.weight": "model--00004-of-00007.safetensors",
-    "block.3.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
-    "block.3.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.3.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
-    "block.3.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
-    "block.3.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
-    "block.3.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
-    "block.3.mlp.norm.scale": "model--00004-of-00007.safetensors",
-    "block.30.attn.norm.scale": "model--00004-of-00007.safetensors",
-    "block.30.attn.out.bias": "model--00004-of-00007.safetensors",
-    "block.30.attn.out.weight": "model--00004-of-00007.safetensors",
-    "block.30.attn.qkv.bias": "model--00004-of-00007.safetensors",
-    "block.30.attn.qkv.weight": "model--00004-of-00007.safetensors",
-    "block.30.attn.sinks": "model--00004-of-00007.safetensors",
-    "block.30.mlp.gate.bias": "model--00004-of-00007.safetensors",
-    "block.30.mlp.gate.weight": "model--00004-of-00007.safetensors",
-    "block.30.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
-    "block.30.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.30.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
-    "block.30.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
-    "block.30.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.30.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
-    "block.30.mlp.norm.scale": "model--00005-of-00007.safetensors",
-    "block.31.attn.norm.scale": "model--00005-of-00007.safetensors",
-    "block.31.attn.out.bias": "model--00005-of-00007.safetensors",
-    "block.31.attn.out.weight": "model--00005-of-00007.safetensors",
-    "block.31.attn.qkv.bias": "model--00005-of-00007.safetensors",
-    "block.31.attn.qkv.weight": "model--00005-of-00007.safetensors",
-    "block.31.attn.sinks": "model--00005-of-00007.safetensors",
-    "block.31.mlp.gate.bias": "model--00005-of-00007.safetensors",
-    "block.31.mlp.gate.weight": "model--00005-of-00007.safetensors",
-    "block.31.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
-    "block.31.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.31.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
-    "block.31.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
-    "block.31.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.31.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
-    "block.31.mlp.norm.scale": "model--00005-of-00007.safetensors",
-    "block.32.attn.norm.scale": "model--00005-of-00007.safetensors",
-    "block.32.attn.out.bias": "model--00005-of-00007.safetensors",
-    "block.32.attn.out.weight": "model--00005-of-00007.safetensors",
-    "block.32.attn.qkv.bias": "model--00005-of-00007.safetensors",
-    "block.32.attn.qkv.weight": "model--00005-of-00007.safetensors",
-    "block.32.attn.sinks": "model--00005-of-00007.safetensors",
-    "block.32.mlp.gate.bias": "model--00005-of-00007.safetensors",
-    "block.32.mlp.gate.weight": "model--00005-of-00007.safetensors",
-    "block.32.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
-    "block.32.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.32.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
-    "block.32.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
-    "block.32.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.32.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
-    "block.32.mlp.norm.scale": "model--00005-of-00007.safetensors",
-    "block.33.attn.norm.scale": "model--00005-of-00007.safetensors",
-    "block.33.attn.out.bias": "model--00005-of-00007.safetensors",
-    "block.33.attn.out.weight": "model--00005-of-00007.safetensors",
-    "block.33.attn.qkv.bias": "model--00005-of-00007.safetensors",
-    "block.33.attn.qkv.weight": "model--00005-of-00007.safetensors",
-    "block.33.attn.sinks": "model--00005-of-00007.safetensors",
-    "block.33.mlp.gate.bias": "model--00005-of-00007.safetensors",
-    "block.33.mlp.gate.weight": "model--00005-of-00007.safetensors",
-    "block.33.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
-    "block.33.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.33.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
-    "block.33.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
-    "block.33.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.33.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
-    "block.33.mlp.norm.scale": "model--00005-of-00007.safetensors",
-    "block.34.attn.norm.scale": "model--00005-of-00007.safetensors",
-    "block.34.attn.out.bias": "model--00005-of-00007.safetensors",
-    "block.34.attn.out.weight": "model--00005-of-00007.safetensors",
-    "block.34.attn.qkv.bias": "model--00005-of-00007.safetensors",
-    "block.34.attn.qkv.weight": "model--00005-of-00007.safetensors",
-    "block.34.attn.sinks": "model--00005-of-00007.safetensors",
-    "block.34.mlp.gate.bias": "model--00005-of-00007.safetensors",
-    "block.34.mlp.gate.weight": "model--00005-of-00007.safetensors",
-    "block.34.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
-    "block.34.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.34.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
-    "block.34.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
-    "block.34.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.34.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
-    "block.34.mlp.norm.scale": "model--00005-of-00007.safetensors",
-    "block.35.attn.norm.scale": "model--00005-of-00007.safetensors",
-    "block.35.attn.out.bias": "model--00005-of-00007.safetensors",
-    "block.35.attn.out.weight": "model--00005-of-00007.safetensors",
-    "block.35.attn.qkv.bias": "model--00005-of-00007.safetensors",
-    "block.35.attn.qkv.weight": "model--00005-of-00007.safetensors",
-    "block.35.attn.sinks": "model--00005-of-00007.safetensors",
-    "block.35.mlp.gate.bias": "model--00005-of-00007.safetensors",
-    "block.35.mlp.gate.weight": "model--00005-of-00007.safetensors",
-    "block.35.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
-    "block.35.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.35.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
-    "block.35.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
-    "block.35.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
-    "block.35.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
-    "block.35.mlp.norm.scale": "model--00005-of-00007.safetensors",
-    "block.4.attn.norm.scale": "model--00005-of-00007.safetensors",
-    "block.4.attn.out.bias": "model--00005-of-00007.safetensors",
-    "block.4.attn.out.weight": "model--00005-of-00007.safetensors",
-    "block.4.attn.qkv.bias": "model--00005-of-00007.safetensors",
-    "block.4.attn.qkv.weight": "model--00005-of-00007.safetensors",
-    "block.4.attn.sinks": "model--00005-of-00007.safetensors",
-    "block.4.mlp.gate.bias": "model--00005-of-00007.safetensors",
-    "block.4.mlp.gate.weight": "model--00005-of-00007.safetensors",
-    "block.4.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
-    "block.4.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.4.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
-    "block.4.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
-    "block.4.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.4.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
-    "block.4.mlp.norm.scale": "model--00006-of-00007.safetensors",
-    "block.5.attn.norm.scale": "model--00006-of-00007.safetensors",
-    "block.5.attn.out.bias": "model--00006-of-00007.safetensors",
-    "block.5.attn.out.weight": "model--00006-of-00007.safetensors",
-    "block.5.attn.qkv.bias": "model--00006-of-00007.safetensors",
-    "block.5.attn.qkv.weight": "model--00006-of-00007.safetensors",
-    "block.5.attn.sinks": "model--00006-of-00007.safetensors",
-    "block.5.mlp.gate.bias": "model--00006-of-00007.safetensors",
-    "block.5.mlp.gate.weight": "model--00006-of-00007.safetensors",
-    "block.5.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
-    "block.5.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.5.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
-    "block.5.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
-    "block.5.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.5.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
-    "block.5.mlp.norm.scale": "model--00006-of-00007.safetensors",
-    "block.6.attn.norm.scale": "model--00006-of-00007.safetensors",
-    "block.6.attn.out.bias": "model--00006-of-00007.safetensors",
-    "block.6.attn.out.weight": "model--00006-of-00007.safetensors",
-    "block.6.attn.qkv.bias": "model--00006-of-00007.safetensors",
-    "block.6.attn.qkv.weight": "model--00006-of-00007.safetensors",
-    "block.6.attn.sinks": "model--00006-of-00007.safetensors",
-    "block.6.mlp.gate.bias": "model--00006-of-00007.safetensors",
-    "block.6.mlp.gate.weight": "model--00006-of-00007.safetensors",
-    "block.6.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
-    "block.6.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.6.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
-    "block.6.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
-    "block.6.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.6.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
-    "block.6.mlp.norm.scale": "model--00006-of-00007.safetensors",
-    "block.7.attn.norm.scale": "model--00006-of-00007.safetensors",
-    "block.7.attn.out.bias": "model--00006-of-00007.safetensors",
-    "block.7.attn.out.weight": "model--00006-of-00007.safetensors",
-    "block.7.attn.qkv.bias": "model--00006-of-00007.safetensors",
-    "block.7.attn.qkv.weight": "model--00006-of-00007.safetensors",
-    "block.7.attn.sinks": "model--00006-of-00007.safetensors",
-    "block.7.mlp.gate.bias": "model--00006-of-00007.safetensors",
-    "block.7.mlp.gate.weight": "model--00006-of-00007.safetensors",
-    "block.7.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
-    "block.7.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.7.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
-    "block.7.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
-    "block.7.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.7.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
-    "block.7.mlp.norm.scale": "model--00006-of-00007.safetensors",
-    "block.8.attn.norm.scale": "model--00006-of-00007.safetensors",
-    "block.8.attn.out.bias": "model--00006-of-00007.safetensors",
-    "block.8.attn.out.weight": "model--00006-of-00007.safetensors",
-    "block.8.attn.qkv.bias": "model--00006-of-00007.safetensors",
-    "block.8.attn.qkv.weight": "model--00006-of-00007.safetensors",
-    "block.8.attn.sinks": "model--00006-of-00007.safetensors",
-    "block.8.mlp.gate.bias": "model--00006-of-00007.safetensors",
-    "block.8.mlp.gate.weight": "model--00006-of-00007.safetensors",
-    "block.8.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
-    "block.8.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.8.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
-    "block.8.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
-    "block.8.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.8.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
-    "block.8.mlp.norm.scale": "model--00006-of-00007.safetensors",
-    "block.9.attn.norm.scale": "model--00006-of-00007.safetensors",
-    "block.9.attn.out.bias": "model--00006-of-00007.safetensors",
-    "block.9.attn.out.weight": "model--00006-of-00007.safetensors",
-    "block.9.attn.qkv.bias": "model--00006-of-00007.safetensors",
-    "block.9.attn.qkv.weight": "model--00006-of-00007.safetensors",
-    "block.9.attn.sinks": "model--00006-of-00007.safetensors",
-    "block.9.mlp.gate.bias": "model--00006-of-00007.safetensors",
-    "block.9.mlp.gate.weight": "model--00006-of-00007.safetensors",
-    "block.9.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
-    "block.9.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.9.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
-    "block.9.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
-    "block.9.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
-    "block.9.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
-    "block.9.mlp.norm.scale": "model--00006-of-00007.safetensors",
-    "embedding.weight": "model--00007-of-00007.safetensors",
-    "norm.scale": "model--00007-of-00007.safetensors",
-    "unembedding.weight": "model--00007-of-00007.safetensors"
-  }
-}

special_tokens_map.json

@@ -1,5 +0,0 @@
-{
-  "bos_token": "<|startoftext|>",
-  "eos_token": "<|return|>",
-  "pad_token": "<|endoftext|>"
-}

tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
-size 27868174

tokenizer_config.json

@@ -1,183 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "199998": {
-      "content": "<|startoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "199999": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200000": {
-      "content": "<|reserved_200000|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200001": {
-      "content": "<|reserved_200001|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200002": {
-      "content": "<|return|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200003": {
-      "content": "<|constrain|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200004": {
-      "content": "<|reserved_200004|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200005": {
-      "content": "<|channel|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200006": {
-      "content": "<|start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200007": {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200008": {
-      "content": "<|message|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200009": {
-      "content": "<|reserved_200009|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200010": {
-      "content": "<|reserved_200010|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200011": {
-      "content": "<|reserved_200011|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200012": {
-      "content": "<|call|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200013": {
-      "content": "<|reserved_200013|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200014": {
-      "content": "<|reserved_200014|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200015": {
-      "content": "<|reserved_200015|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200016": {
-      "content": "<|reserved_200016|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200017": {
-      "content": "<|reserved_200017|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200018": {
-      "content": "<|endofprompt|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<|startoftext|>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|return|>",
-  "extra_special_tokens": {},
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
-}