| { |
| "_name_or_path": "unsloth/mistral-7b", |
| "architectures": [ |
| "MistralForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "max_position_embeddings": 32768, |
| "model_type": "mistral", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "pad_token_id": 0, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 10000.0, |
| "sliding_window": 4096, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.44.2", |
| "unsloth_version": "2024.9", |
| "use_cache": true, |
| "vocab_size": 32000, |
| "quantization": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine", |
| "model.embed_tokens": { |
| "bits": 8, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.mlp.down_proj": { |
| "bits": 6, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.k_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.q_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.v_proj": { |
| "bits": 6, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.mlp.down_proj": { |
| "bits": 6, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.self_attn.k_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.self_attn.q_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.self_attn.v_proj": { |
| "bits": 6, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.10.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.2.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.3.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.4.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "lm_head": { |
| "bits": 8, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.26.self_attn.k_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| } |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine", |
| "model.embed_tokens": { |
| "bits": 8, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.mlp.down_proj": { |
| "bits": 6, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.k_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.q_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.v_proj": { |
| "bits": 6, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.mlp.down_proj": { |
| "bits": 6, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.self_attn.k_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.self_attn.q_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.1.self_attn.v_proj": { |
| "bits": 6, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.10.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.2.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.3.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.4.self_attn.o_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "lm_head": { |
| "bits": 8, |
| "group_size": 64, |
| "mode": "affine" |
| }, |
| "model.layers.26.self_attn.k_proj": { |
| "bits": 5, |
| "group_size": 64, |
| "mode": "affine" |
| } |
| } |
| } |
