Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +1 -0
- config.json +51 -0
- generation_config.json +11 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
README.md
CHANGED
|
@@ -6,6 +6,7 @@ tags:
|
|
| 6 |
- unsloth
|
| 7 |
- llama
|
| 8 |
- trl
|
|
|
|
| 9 |
license: apache-2.0
|
| 10 |
language:
|
| 11 |
- en
|
|
|
|
| 6 |
- unsloth
|
| 7 |
- llama
|
| 8 |
- trl
|
| 9 |
+
- sft
|
| 10 |
license: apache-2.0
|
| 11 |
language:
|
| 12 |
- en
|
config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128001,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 14336,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 32,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 128004,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"quantization_config": {
|
| 24 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 25 |
+
"bnb_4bit_quant_type": "nf4",
|
| 26 |
+
"bnb_4bit_use_double_quant": true,
|
| 27 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 28 |
+
"llm_int8_has_fp16_weight": false,
|
| 29 |
+
"llm_int8_skip_modules": null,
|
| 30 |
+
"llm_int8_threshold": 6.0,
|
| 31 |
+
"load_in_4bit": true,
|
| 32 |
+
"load_in_8bit": false,
|
| 33 |
+
"quant_method": "bitsandbytes"
|
| 34 |
+
},
|
| 35 |
+
"rms_norm_eps": 1e-05,
|
| 36 |
+
"rope_scaling": {
|
| 37 |
+
"factor": 8.0,
|
| 38 |
+
"high_freq_factor": 4.0,
|
| 39 |
+
"low_freq_factor": 1.0,
|
| 40 |
+
"original_max_position_embeddings": 8192,
|
| 41 |
+
"rope_type": "llama3"
|
| 42 |
+
},
|
| 43 |
+
"rope_theta": 500000.0,
|
| 44 |
+
"tie_word_embeddings": false,
|
| 45 |
+
"torch_dtype": "bfloat16",
|
| 46 |
+
"transformers_version": "4.49.0",
|
| 47 |
+
"unsloth_fixed": true,
|
| 48 |
+
"unsloth_version": "2025.3.9",
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"vocab_size": 128256
|
| 51 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 128001,
|
| 6 |
+
"max_length": 131072,
|
| 7 |
+
"pad_token_id": 128004,
|
| 8 |
+
"temperature": 0.6,
|
| 9 |
+
"top_p": 0.95,
|
| 10 |
+
"transformers_version": "4.49.0"
|
| 11 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a367bf42441456af570b26e101347ad0eedc776f54b14a0ea744194a31701d9
|
| 3 |
+
size 4913512950
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d617c29ce19434a764165114c4e7825cf927f90b3bb45fd181732a0dd13b0a57
|
| 3 |
+
size 1050673280
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|