Commit
•
8695904
1
Parent(s):
cbb5ecc
Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +5 -3
- config.json +43 -0
- generation_config.json +10 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
README.md
CHANGED
|
@@ -1,4 +1,7 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
license: apache-2.0
|
|
@@ -11,9 +14,8 @@ tags:
|
|
| 11 |
- python
|
| 12 |
- llama3.1
|
| 13 |
- llama python models
|
| 14 |
-
|
| 15 |
-
-
|
| 16 |
-
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 17 |
---
|
| 18 |
|
| 19 |
# Uploaded model
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 3 |
+
datasets:
|
| 4 |
+
- NuclearAi/Nuke-Python-Verse
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
license: apache-2.0
|
|
|
|
| 14 |
- python
|
| 15 |
- llama3.1
|
| 16 |
- llama python models
|
| 17 |
+
- unsloth
|
| 18 |
+
- trl
|
|
|
|
| 19 |
---
|
| 20 |
|
| 21 |
# Uploaded model
|
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "unsloth/llama-3-8b-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 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 8192,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pad_token_id": 128255,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"quantization_config": {
|
| 23 |
+
"bnb_4bit_compute_dtype": "float16",
|
| 24 |
+
"bnb_4bit_quant_type": "nf4",
|
| 25 |
+
"bnb_4bit_use_double_quant": true,
|
| 26 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 27 |
+
"llm_int8_has_fp16_weight": false,
|
| 28 |
+
"llm_int8_skip_modules": null,
|
| 29 |
+
"llm_int8_threshold": 6.0,
|
| 30 |
+
"load_in_4bit": true,
|
| 31 |
+
"load_in_8bit": false,
|
| 32 |
+
"quant_method": "bitsandbytes"
|
| 33 |
+
},
|
| 34 |
+
"rms_norm_eps": 1e-05,
|
| 35 |
+
"rope_scaling": null,
|
| 36 |
+
"rope_theta": 500000.0,
|
| 37 |
+
"tie_word_embeddings": false,
|
| 38 |
+
"torch_dtype": "float16",
|
| 39 |
+
"transformers_version": "4.44.2",
|
| 40 |
+
"unsloth_version": "2024.8",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 128256
|
| 43 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 128001,
|
| 5 |
+
"max_length": 8192,
|
| 6 |
+
"pad_token_id": 128255,
|
| 7 |
+
"temperature": 0.6,
|
| 8 |
+
"top_p": 0.9,
|
| 9 |
+
"transformers_version": "4.44.2"
|
| 10 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2759a6edde8a4f6021bb838982826e22db0c359c5a7ea0e65ba6523fd991233
|
| 3 |
+
size 4652072877
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4f15e64381b74dcb7857c03cbfb62806534f7582ab885c738980a12e5b78989
|
| 3 |
+
size 1050673280
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|