Upload MistralForCausalLM
Browse files- config.json +39 -0
- generation_config.json +7 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "alnrg2arg/blockchainlabs_7B_merged_test2_4_prune",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"quantization_config": {
|
19 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
20 |
+
"bnb_4bit_quant_type": "nf4",
|
21 |
+
"bnb_4bit_use_double_quant": true,
|
22 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
23 |
+
"llm_int8_has_fp16_weight": false,
|
24 |
+
"llm_int8_skip_modules": null,
|
25 |
+
"llm_int8_threshold": 6.0,
|
26 |
+
"load_in_4bit": true,
|
27 |
+
"load_in_8bit": false,
|
28 |
+
"quant_method": "bitsandbytes"
|
29 |
+
},
|
30 |
+
"rms_norm_eps": 1e-05,
|
31 |
+
"rope_theta": 10000.0,
|
32 |
+
"sliding_window": 4096,
|
33 |
+
"tie_word_embeddings": false,
|
34 |
+
"torch_dtype": "bfloat16",
|
35 |
+
"transformers_version": "4.37.0",
|
36 |
+
"unsloth_version": "2024.1",
|
37 |
+
"use_cache": false,
|
38 |
+
"vocab_size": 32000
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.37.0",
|
6 |
+
"use_cache": false
|
7 |
+
}
|
model-00001-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c2a595164fb87f7fe9e7ea876cc5926bd6d9ddec3dd02b6da274e0b1d732969
|
3 |
+
size 4810124586
|
model-00002-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc7ad6bb31f1d6eea4a609379b912716f7af0bb08b8116760c34b62b13913f5b
|
3 |
+
size 4851164435
|
model-00003-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83fe0a36cd11fe7899172fa6c80aae0e4c3e16cdfc38cf5f8b020ee10034cd98
|
3 |
+
size 4783812213
|
model-00004-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:403d85780999a2568b23516ae6aeee57aea3778415c609b358da36e320de155d
|
3 |
+
size 4851164656
|
model-00005-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:755283f9b6cf6d0ff8e9b6a2d1f5d0187b35ce8c7f8f92879137fe51656b0238
|
3 |
+
size 4783812220
|
model-00006-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6869f0a63fde6c1a53a6b223dd8f367cd4b44d2fb75dd6732cf23e22b680189
|
3 |
+
size 4473241516
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|