初始化项目，由ModelHub XC社区提供模型
Model: ddh0/Meta-Llama-3-8B-Instruct-bf16-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Meta-Llama-3-8B-Instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
3
Meta-Llama-3-8B-Instruct-bf16.gguf
Normal file
3
Meta-Llama-3-8B-Instruct-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d0830c88d8f3f3947531be06e92e676b0dbc12395181592d59522df7d1438c38
|
||||||
|
size 16068890912
|
||||||
89
README.md
Normal file
89
README.md
Normal file
@@ -0,0 +1,89 @@
|
|||||||
|
---
|
||||||
|
license: llama3
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
---
|
||||||
|
|
||||||
|
# Meta-Llama-3-8B-Instruct-bf16-GGUF
|
||||||
|
|
||||||
|
This is [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct), converted to GGUF without changing tensor data type. Moreover, the new correct pre-tokenizer `llama-bpe` is used ([ref](https://github.com/ggerganov/llama.cpp/pull/6745#issuecomment-2094991999)), and the EOS token is correctly set to `<|eot_id|>` ([ref](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/commit/a8977699a3d0820e80129fb3c93c20fbd9972c41)).
|
||||||
|
|
||||||
|
The `llama.cpp` output for this model is shown below for reference.
|
||||||
|
|
||||||
|
```
|
||||||
|
Log start
|
||||||
|
main: build = 2842 (18e43766)
|
||||||
|
main: built with cc (Debian 12.2.0-14) 12.2.0 for x86_64-linux-gnu
|
||||||
|
main: seed = 1715355914
|
||||||
|
llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from /media/dylan/SanDisk/LLMs/Meta-Llama-3-8B-Instruct-bf16.gguf (version GGUF V3 (latest))
|
||||||
|
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
|
||||||
|
llama_model_loader: - kv 0: general.architecture str = llama
|
||||||
|
llama_model_loader: - kv 1: general.name str = Meta-Llama-3-8B-Instruct
|
||||||
|
llama_model_loader: - kv 2: llama.block_count u32 = 32
|
||||||
|
llama_model_loader: - kv 3: llama.context_length u32 = 8192
|
||||||
|
llama_model_loader: - kv 4: llama.embedding_length u32 = 4096
|
||||||
|
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336
|
||||||
|
llama_model_loader: - kv 6: llama.attention.head_count u32 = 32
|
||||||
|
llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8
|
||||||
|
llama_model_loader: - kv 8: llama.rope.freq_base f32 = 500000.000000
|
||||||
|
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
|
||||||
|
llama_model_loader: - kv 10: general.file_type u32 = 32
|
||||||
|
llama_model_loader: - kv 11: llama.vocab_size u32 = 128256
|
||||||
|
llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128
|
||||||
|
llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2
|
||||||
|
llama_model_loader: - kv 14: tokenizer.ggml.pre str = llama-bpe
|
||||||
|
llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ...
|
||||||
|
llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
|
||||||
|
llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
|
||||||
|
llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 128000
|
||||||
|
llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 128009
|
||||||
|
llama_model_loader: - kv 20: tokenizer.chat_template str = {% set loop_messages = messages %}{% ...
|
||||||
|
llama_model_loader: - kv 21: general.quantization_version u32 = 2
|
||||||
|
llama_model_loader: - type f32: 65 tensors
|
||||||
|
llama_model_loader: - type bf16: 226 tensors
|
||||||
|
llm_load_vocab: special tokens definition check successful ( 256/128256 ).
|
||||||
|
llm_load_print_meta: format = GGUF V3 (latest)
|
||||||
|
llm_load_print_meta: arch = llama
|
||||||
|
llm_load_print_meta: vocab type = BPE
|
||||||
|
llm_load_print_meta: n_vocab = 128256
|
||||||
|
llm_load_print_meta: n_merges = 280147
|
||||||
|
llm_load_print_meta: n_ctx_train = 8192
|
||||||
|
llm_load_print_meta: n_embd = 4096
|
||||||
|
llm_load_print_meta: n_head = 32
|
||||||
|
llm_load_print_meta: n_head_kv = 8
|
||||||
|
llm_load_print_meta: n_layer = 32
|
||||||
|
llm_load_print_meta: n_rot = 128
|
||||||
|
llm_load_print_meta: n_embd_head_k = 128
|
||||||
|
llm_load_print_meta: n_embd_head_v = 128
|
||||||
|
llm_load_print_meta: n_gqa = 4
|
||||||
|
llm_load_print_meta: n_embd_k_gqa = 1024
|
||||||
|
llm_load_print_meta: n_embd_v_gqa = 1024
|
||||||
|
llm_load_print_meta: f_norm_eps = 0.0e+00
|
||||||
|
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
|
||||||
|
llm_load_print_meta: f_clamp_kqv = 0.0e+00
|
||||||
|
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
|
||||||
|
llm_load_print_meta: f_logit_scale = 0.0e+00
|
||||||
|
llm_load_print_meta: n_ff = 14336
|
||||||
|
llm_load_print_meta: n_expert = 0
|
||||||
|
llm_load_print_meta: n_expert_used = 0
|
||||||
|
llm_load_print_meta: causal attn = 1
|
||||||
|
llm_load_print_meta: pooling type = 0
|
||||||
|
llm_load_print_meta: rope type = 0
|
||||||
|
llm_load_print_meta: rope scaling = linear
|
||||||
|
llm_load_print_meta: freq_base_train = 500000.0
|
||||||
|
llm_load_print_meta: freq_scale_train = 1
|
||||||
|
llm_load_print_meta: n_yarn_orig_ctx = 8192
|
||||||
|
llm_load_print_meta: rope_finetuned = unknown
|
||||||
|
llm_load_print_meta: ssm_d_conv = 0
|
||||||
|
llm_load_print_meta: ssm_d_inner = 0
|
||||||
|
llm_load_print_meta: ssm_d_state = 0
|
||||||
|
llm_load_print_meta: ssm_dt_rank = 0
|
||||||
|
llm_load_print_meta: model type = 8B
|
||||||
|
llm_load_print_meta: model ftype = BF16
|
||||||
|
llm_load_print_meta: model params = 8.03 B
|
||||||
|
llm_load_print_meta: model size = 14.96 GiB (16.00 BPW)
|
||||||
|
llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct
|
||||||
|
llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>'
|
||||||
|
llm_load_print_meta: EOS token = 128009 '<|eot_id|>'
|
||||||
|
llm_load_print_meta: LF token = 128 'Ä'
|
||||||
|
llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
|
||||||
|
```
|
||||||
Reference in New Issue
Block a user