Trained with Unsloth
Browse files- README.md +5 -2
- config.json +30 -0
- generation_config.json +14 -0
- model.safetensors +3 -0
README.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
---
|
| 2 |
-
license: cc-by-4.0
|
| 3 |
datasets:
|
| 4 |
- AI-MO/NuminaMath-CoT
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
library_name: transformers
|
|
|
|
| 8 |
tags:
|
| 9 |
- text-generation-inference
|
| 10 |
- chat
|
|
@@ -12,4 +12,7 @@ tags:
|
|
| 12 |
- conversational
|
| 13 |
- math
|
| 14 |
- maths
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
datasets:
|
| 3 |
- AI-MO/NuminaMath-CoT
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
library_name: transformers
|
| 7 |
+
license: cc-by-4.0
|
| 8 |
tags:
|
| 9 |
- text-generation-inference
|
| 10 |
- chat
|
|
|
|
| 12 |
- conversational
|
| 13 |
- math
|
| 14 |
- maths
|
| 15 |
+
- unsloth
|
| 16 |
+
- trl
|
| 17 |
+
- sft
|
| 18 |
+
---
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 24,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 14,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"sliding_window": 32768,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.42.4",
|
| 26 |
+
"unsloth_version": "2024.7",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.42.4"
|
| 14 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9ba56437ce3bcf47c1bd3aa731f89c3967786d88a4fcc24e0aa1974d62562a5
|
| 3 |
+
size 988097824
|