ranamhamoud
commited on
Upload LlamaForCausalLM
Browse files- README.md +3 -0
- config.json +51 -0
- generation_config.json +9 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
README.md
CHANGED
@@ -1,3 +1,6 @@
|
|
1 |
---
|
2 |
license: mit
|
|
|
|
|
|
|
3 |
---
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
tags:
|
4 |
+
- trl
|
5 |
+
- sft
|
6 |
---
|
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Llama-3.1-8B",
|
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 |
+
"pretraining_tp": 1,
|
22 |
+
"quantization_config": {
|
23 |
+
"_load_in_4bit": true,
|
24 |
+
"_load_in_8bit": false,
|
25 |
+
"bnb_4bit_compute_dtype": "float16",
|
26 |
+
"bnb_4bit_quant_storage": "uint8",
|
27 |
+
"bnb_4bit_quant_type": "nf4",
|
28 |
+
"bnb_4bit_use_double_quant": false,
|
29 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
30 |
+
"llm_int8_has_fp16_weight": false,
|
31 |
+
"llm_int8_skip_modules": null,
|
32 |
+
"llm_int8_threshold": 6.0,
|
33 |
+
"load_in_4bit": true,
|
34 |
+
"load_in_8bit": false,
|
35 |
+
"quant_method": "bitsandbytes"
|
36 |
+
},
|
37 |
+
"rms_norm_eps": 1e-05,
|
38 |
+
"rope_scaling": {
|
39 |
+
"factor": 8.0,
|
40 |
+
"high_freq_factor": 4.0,
|
41 |
+
"low_freq_factor": 1.0,
|
42 |
+
"original_max_position_embeddings": 8192,
|
43 |
+
"rope_type": "llama3"
|
44 |
+
},
|
45 |
+
"rope_theta": 500000.0,
|
46 |
+
"tie_word_embeddings": false,
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.47.1",
|
49 |
+
"use_cache": false,
|
50 |
+
"vocab_size": 128256
|
51 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 128000,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 128001,
|
6 |
+
"temperature": 0.6,
|
7 |
+
"top_p": 0.9,
|
8 |
+
"transformers_version": "4.47.1"
|
9 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcaacc7121b5d2be11d4fe85e40e73269e3a428057dad0325800b8af53f2e9fa
|
3 |
+
size 4988429954
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cee6225f5d03c7909eb4a4bf6987db3e7f13ab9433655a57cae928e900c7747
|
3 |
+
size 3195891278
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|