Upload MixtralForCausalLM
Browse files- config.json +48 -0
- generation_config.json +6 -0
- model-00001-of-00009.safetensors +3 -0
- model-00002-of-00009.safetensors +3 -0
- model-00003-of-00009.safetensors +3 -0
- model-00004-of-00009.safetensors +3 -0
- model-00005-of-00009.safetensors +3 -0
- model-00006-of-00009.safetensors +3 -0
- model-00007-of-00009.safetensors +3 -0
- model-00008-of-00009.safetensors +3 -0
- model-00009-of-00009.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MixtralForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 5120,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 13824,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "mixtral",
|
| 17 |
+
"num_attention_heads": 40,
|
| 18 |
+
"num_experts_per_tok": 2,
|
| 19 |
+
"num_hidden_layers": 40,
|
| 20 |
+
"num_key_value_heads": 40,
|
| 21 |
+
"num_local_experts": 8,
|
| 22 |
+
"output_router_logits": false,
|
| 23 |
+
"quantization_config": {
|
| 24 |
+
"_load_in_4bit": true,
|
| 25 |
+
"_load_in_8bit": false,
|
| 26 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 27 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 28 |
+
"bnb_4bit_quant_type": "nf4",
|
| 29 |
+
"bnb_4bit_use_double_quant": false,
|
| 30 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 31 |
+
"llm_int8_has_fp16_weight": false,
|
| 32 |
+
"llm_int8_skip_modules": null,
|
| 33 |
+
"llm_int8_threshold": 6.0,
|
| 34 |
+
"load_in_4bit": true,
|
| 35 |
+
"load_in_8bit": false,
|
| 36 |
+
"quant_method": "bitsandbytes"
|
| 37 |
+
},
|
| 38 |
+
"rms_norm_eps": 1e-05,
|
| 39 |
+
"rope_theta": 10000,
|
| 40 |
+
"router_aux_loss_coef": 0.01,
|
| 41 |
+
"router_jitter_noise": 0.0,
|
| 42 |
+
"sliding_window": null,
|
| 43 |
+
"tie_word_embeddings": false,
|
| 44 |
+
"torch_dtype": "float16",
|
| 45 |
+
"transformers_version": "4.51.2",
|
| 46 |
+
"use_cache": true,
|
| 47 |
+
"vocab_size": 99584
|
| 48 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.51.2"
|
| 6 |
+
}
|
model-00001-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7085f62c922ff2015f37567b59003c0b9ea062c9ec732017c3bc508cc19f42c3
|
| 3 |
+
size 4998334764
|
model-00002-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a3274b749c3b2100bf73839dc8f5d62397f57ccd090a3111aa7509624653e5a
|
| 3 |
+
size 4993175862
|
model-00003-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61495560636993c7f350d05b2accf480a375b1efc8e62977327bd1752efb87e7
|
| 3 |
+
size 4993176310
|
model-00004-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b2020911f7ebf7db287f1c2ecb296f2df322df557f32e03e08a61568ed56c84
|
| 3 |
+
size 4993176446
|
model-00005-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe461786a797c1649361ad3d9d85d1569dcde2ddc09e3f1a3bb3c56dc36809e4
|
| 3 |
+
size 4993176446
|
model-00006-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:189a53b7f22ee2e755ce95d67ab5e584ec25723742613c45dbe4b8874d142595
|
| 3 |
+
size 4993176446
|
model-00007-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3bd34fb88f4ff1339d9a9e58aa9a7e872570a8e137feeff30c87689895639f4
|
| 3 |
+
size 4993176446
|
model-00008-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f92ab5a1c93605beaf360588fba7faa72284c8cd596dc40e03f15ceb7b57909
|
| 3 |
+
size 4993176446
|
model-00009-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3442301c75a77ce84c1809c6b8f4f6d9ca0187ed749d6a5d035c312e91ab7ab
|
| 3 |
+
size 2671353066
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|