Upload MixtralForCausalLM
Browse files- config.json +42 -0
- generation_config.json +6 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixtralForCausalLM"
|
| 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": "mixtral",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_experts_per_tok": 2,
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"num_local_experts": 8,
|
| 20 |
+
"output_router_logits": false,
|
| 21 |
+
"quantization_config": {
|
| 22 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 23 |
+
"bnb_4bit_quant_type": "fp4",
|
| 24 |
+
"bnb_4bit_use_double_quant": true,
|
| 25 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 26 |
+
"llm_int8_has_fp16_weight": false,
|
| 27 |
+
"llm_int8_skip_modules": null,
|
| 28 |
+
"llm_int8_threshold": 6.0,
|
| 29 |
+
"load_in_4bit": true,
|
| 30 |
+
"load_in_8bit": false,
|
| 31 |
+
"quant_method": "bitsandbytes"
|
| 32 |
+
},
|
| 33 |
+
"rms_norm_eps": 1e-05,
|
| 34 |
+
"rope_theta": 1000000.0,
|
| 35 |
+
"router_aux_loss_coef": 0.02,
|
| 36 |
+
"sliding_window": null,
|
| 37 |
+
"tie_word_embeddings": false,
|
| 38 |
+
"torch_dtype": "float16",
|
| 39 |
+
"transformers_version": "4.37.0.dev0",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 32000
|
| 42 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.37.0.dev0"
|
| 6 |
+
}
|
model-00001-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbd70f36d16e724d8ab9ee10ba759e8cf3333e65eb52e3d2fd8225fa33915f0e
|
| 3 |
+
size 4988290003
|
model-00002-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4ef5c86d7eb87fdb7156eb19b09fcc8a3616b8b4f410b09e4508c62ce461f51
|
| 3 |
+
size 4977128621
|
model-00003-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd19ad60220852d0adeb06eb79a880e84c8ef5c7b5940a24986920be9d9b9b04
|
| 3 |
+
size 4998809858
|
model-00004-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3da11a2294a20fe71b2d8eef663e1147616401878260d14e4419da600456d73e
|
| 3 |
+
size 4998809875
|
model-00005-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3da6e3ae589e01edcf404af44e318bd281813d99e0ed82d58a178117752ffb4a
|
| 3 |
+
size 4520854881
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|