Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +2 -1
- config.json +50 -0
- generation_config.json +8 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
tags:
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for Model ID
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- unsloth
|
| 5 |
---
|
| 6 |
|
| 7 |
# Model Card for Model ID
|
config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 12288,
|
| 14 |
+
"max_position_embeddings": 131072,
|
| 15 |
+
"max_window_layers": 36,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 36,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pad_token_id": 151654,
|
| 21 |
+
"quantization_config": {
|
| 22 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 23 |
+
"bnb_4bit_quant_type": "nf4",
|
| 24 |
+
"bnb_4bit_use_double_quant": true,
|
| 25 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 26 |
+
"llm_int8_has_fp16_weight": false,
|
| 27 |
+
"llm_int8_skip_modules": null,
|
| 28 |
+
"llm_int8_threshold": 6.0,
|
| 29 |
+
"load_in_4bit": true,
|
| 30 |
+
"load_in_8bit": false,
|
| 31 |
+
"quant_method": "bitsandbytes"
|
| 32 |
+
},
|
| 33 |
+
"rms_norm_eps": 1e-06,
|
| 34 |
+
"rope_scaling": {
|
| 35 |
+
"attn_factor": 0.8782488562869419,
|
| 36 |
+
"factor": 4.0,
|
| 37 |
+
"original_max_position_embeddings": 32768,
|
| 38 |
+
"rope_type": "yarn"
|
| 39 |
+
},
|
| 40 |
+
"rope_theta": 1000000,
|
| 41 |
+
"sliding_window": null,
|
| 42 |
+
"tie_word_embeddings": false,
|
| 43 |
+
"torch_dtype": "bfloat16",
|
| 44 |
+
"transformers_version": "4.52.1",
|
| 45 |
+
"unsloth_fixed": true,
|
| 46 |
+
"unsloth_version": "2025.6.1",
|
| 47 |
+
"use_cache": true,
|
| 48 |
+
"use_sliding_window": false,
|
| 49 |
+
"vocab_size": 151936
|
| 50 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"max_length": 131072,
|
| 6 |
+
"pad_token_id": 151654,
|
| 7 |
+
"transformers_version": "4.52.1"
|
| 8 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:609bdf516c9791f05b55b69f4ef2b0c6e7402ae6ea889ff5e53ea89b5f64be4c
|
| 3 |
+
size 4975323565
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d199b122e441159d8656c137aa73a0b7aaba2174c50097b9df36d9569c2b4632
|
| 3 |
+
size 2467653385
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|