Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +1 -0
- config.json +56 -0
- generation_config.json +15 -0
- model.safetensors +3 -0
README.md
CHANGED
|
@@ -6,6 +6,7 @@ tags:
|
|
| 6 |
- unsloth
|
| 7 |
- qwen2
|
| 8 |
- trl
|
|
|
|
| 9 |
license: apache-2.0
|
| 10 |
language:
|
| 11 |
- en
|
|
|
|
| 6 |
- unsloth
|
| 7 |
- qwen2
|
| 8 |
- trl
|
| 9 |
+
- sft
|
| 10 |
license: apache-2.0
|
| 11 |
language:
|
| 12 |
- en
|
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_act": "silu",
|
| 8 |
+
"hidden_size": 896,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 4864,
|
| 11 |
+
"layer_types": [
|
| 12 |
+
"full_attention",
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention"
|
| 36 |
+
],
|
| 37 |
+
"max_position_embeddings": 32768,
|
| 38 |
+
"max_window_layers": 21,
|
| 39 |
+
"model_type": "qwen2",
|
| 40 |
+
"num_attention_heads": 14,
|
| 41 |
+
"num_hidden_layers": 24,
|
| 42 |
+
"num_key_value_heads": 2,
|
| 43 |
+
"pad_token_id": 151654,
|
| 44 |
+
"rms_norm_eps": 1e-06,
|
| 45 |
+
"rope_scaling": null,
|
| 46 |
+
"rope_theta": 1000000.0,
|
| 47 |
+
"sliding_window": null,
|
| 48 |
+
"tie_word_embeddings": true,
|
| 49 |
+
"torch_dtype": "float16",
|
| 50 |
+
"transformers_version": "4.55.4",
|
| 51 |
+
"unsloth_fixed": true,
|
| 52 |
+
"unsloth_version": "2025.8.10",
|
| 53 |
+
"use_cache": true,
|
| 54 |
+
"use_sliding_window": false,
|
| 55 |
+
"vocab_size": 151936
|
| 56 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"max_length": 32768,
|
| 9 |
+
"pad_token_id": 151654,
|
| 10 |
+
"repetition_penalty": 1.1,
|
| 11 |
+
"temperature": 0.7,
|
| 12 |
+
"top_k": 20,
|
| 13 |
+
"top_p": 0.8,
|
| 14 |
+
"transformers_version": "4.55.4"
|
| 15 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bac404ae74d644016cc09d230fa6ac69f6b2f1d272ec18d7e8baac55e9d1aceb
|
| 3 |
+
size 988097536
|