Trained with Unsloth
Browse files- README.md +2 -0
- config.json +2 -14
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
README.md
CHANGED
@@ -6,6 +6,8 @@ tags:
|
|
6 |
- search
|
7 |
- language-to-query
|
8 |
- unsloth
|
|
|
|
|
9 |
library_name: transformers
|
10 |
pipeline_tag: text2text-generation
|
11 |
license: llama2
|
|
|
6 |
- search
|
7 |
- language-to-query
|
8 |
- unsloth
|
9 |
+
- trl
|
10 |
+
- sft
|
11 |
library_name: transformers
|
12 |
pipeline_tag: text2text-generation
|
13 |
license: llama2
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -20,18 +20,6 @@
|
|
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,
|
@@ -45,7 +33,7 @@
|
|
45 |
"torch_dtype": "bfloat16",
|
46 |
"transformers_version": "4.49.0",
|
47 |
"unsloth_fixed": true,
|
48 |
-
"unsloth_version": "2025.3.
|
49 |
"use_cache": true,
|
50 |
"vocab_size": 128256
|
51 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "unsloth/llama-3.1-8b-instruct-unsloth-bnb-4bit",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
20 |
"num_key_value_heads": 8,
|
21 |
"pad_token_id": 128004,
|
22 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"rms_norm_eps": 1e-05,
|
24 |
"rope_scaling": {
|
25 |
"factor": 8.0,
|
|
|
33 |
"torch_dtype": "bfloat16",
|
34 |
"transformers_version": "4.49.0",
|
35 |
"unsloth_fixed": true,
|
36 |
+
"unsloth_version": "2025.3.17",
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 128256
|
39 |
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40b0ec1552855675a5cc976f862891bccdea0ad897bca645aecbb2678c1fad25
|
3 |
+
size 4976698672
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93342d0cee6c773b02b731d6ca3de1b7c0be5d71d87d779c659a7b4af7a016b0
|
3 |
+
size 4999802720
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbe3840ceba1abc7157277bb150b81e70064cbcb3d9d1cec4468858d30a773b3
|
3 |
+
size 4915916176
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86a54960ff965e28132e993299826b9a4a09c153ce202f4523936c5652dce653
|
3 |
+
size 1168138808
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|