Upload GPTNeoXGPTQForCausalLM
Browse files- config.json +26 -0
- gptq_model-4bit-128g.bin +3 -0
- quantize_config.json +8 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./stablelm-tuned-alpha-7b-4bit-128g-descact-sym-true-sequential",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": 0.1,
|
| 8 |
+
"eos_token_id": 0,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_size": 6144,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 24576,
|
| 13 |
+
"layer_norm_eps": 1e-05,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "gpt_neox",
|
| 16 |
+
"num_attention_heads": 48,
|
| 17 |
+
"num_hidden_layers": 16,
|
| 18 |
+
"rotary_emb_base": 10000,
|
| 19 |
+
"rotary_pct": 0.25,
|
| 20 |
+
"tie_word_embeddings": false,
|
| 21 |
+
"torch_dtype": "bfloat16",
|
| 22 |
+
"transformers_version": "4.29.1",
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"use_parallel_residual": true,
|
| 25 |
+
"vocab_size": 50432
|
| 26 |
+
}
|
gptq_model-4bit-128g.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d63047e472199d5f2eb584a06d41f2a599865b6a57a40143c4ef5675223cdda
|
| 3 |
+
size 5278778631
|
quantize_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"group_size": 128,
|
| 4 |
+
"damp_percent": 0.01,
|
| 5 |
+
"desc_act": true,
|
| 6 |
+
"sym": true,
|
| 7 |
+
"true_sequential": true
|
| 8 |
+
}
|